# AgentPMT - Frequently Asked Questions

Total: 199 questions

## General

### Can I ban repeat spammers?
Yes. When you reject a comment you can also ban its author in the same action, preventing them from commenting on your channel again. Bans can be reversed later from YouTube Studio if you change your mind.

### Can I bulk-delete or reject spam comments on my YouTube channel?
Yes. You can reject many comments in a single moderation call and optionally ban their authors at the same time, so clearing a flood of bot spam takes one pass instead of hundreds of manual clicks in YouTube Studio.

### Can I control what the tool is allowed to do?
Yes. The organization key's scopes decide what the tool can read or change. Grant read-only scopes for reporting, or add write scopes to manage members, templates, and recordings.

### Can I control who sees my posts?
Yes. Choose public visibility to reach anyone on LinkedIn, or connections-only for a more private update. You set visibility on each post.

### Can I edit an existing image or keep a product consistent across scenes?
Yes. Attach up to four reference images to guide subject, style, or scene. Reference-image editing keeps the same subject across new backgrounds, so you can place the same product in different settings or carry one look through an entire campaign.

### Can I edit or delete comments I already posted?
Yes — you can update the text of, or permanently delete, any comment your connected account authored. You can't edit other people's comments, but as the channel owner you can moderate them.

### Can I filter and sort search results?
Yes. You can filter videos by date range, region, language, duration, definition, caption availability, license, livestream status, location, and category, and sort by relevance, date, rating, view count, or title.

### Can I post images and videos?
Yes. Upload an image or a video, then publish it as a feed post with your caption. It is a simple two step flow: upload the media, then create the post.

### Can I reuse one document across multiple agents and workflows?
Yes. That is the point. Attach the same document anywhere it is needed, and edit it once to update every agent and workflow that references it -- no more updating the same instructions in many places.

### Can I revoke an agent's access at any time?
Yes. Pause its smart contract, revoke its API keys, or end its session from the dashboard. Every action takes effect within seconds and is recorded in the audit log.

### Can I schedule an email and cancel it later?
Yes. Transactional sends schedule up to 72 hours ahead and campaigns schedule for any future time. Both can be paused, rescheduled, or cancelled before they go out.

### Can I schedule an email and cancel it later?
Yes. Schedule sends up to 72 hours ahead. Scheduled sends can be paused, resumed, or cancelled until shortly before the send time.

### Can I schedule messages to send later?
Yes. Messages can be scheduled from 15 minutes to 7 days in the future. Scheduling sends through your Twilio Messaging Service, so a Messaging Service SID must be set on the credential.

### Can I share articles and links with a preview?
Yes. Share any public URL with optional title and description text, and LinkedIn renders a clean link preview card that helps drive clicks to your blog, product page, or announcement.

### Can I upload audio that was not recorded on a Pocket device?
Yes. Upload an audio file of up to 100 MB from your file storage and Pocket will transcribe and summarize it just like any other recording.

### Can I use more than one account on the same site?
Yes. Connect as many accounts as you want and give each a friendly name, and the agent opens the right one by name.

### Can I use more than one account on the same site?
Yes. Connect as many accounts as you want and give each a friendly helper name; the agent opens the right one by name.

### Can I use my own artwork for textures?
Yes. Give any item, block, or creature a solid color, upload your own image, or use a generated pixel-art sprite — and preview it before you install.

### Can I watch what the agent is doing?
Yes. Sessions are live and you can take over at any moment. The agent can also capture screenshots as it works so you can review each step.

### Can agents assign work to people?
Yes. Use assign_task or update_task with an assignee. Assignees can be a user GID, an email address, or me for the connected account. Email resolution can use an optional workspace_gid.

### Can agents update linked records and lookups?
Yes for links: write linked-record fields as arrays of record IDs. Lookups are read-only; after links are set, re-read the record to see lookup values. For Interface pages, only fields placed on the page are available through page-specific actions.

### Can an AI agent reply to my YouTube comments for me?
Yes. The tool posts top-level comments and replies as your connected account, so an agent can answer questions on a launch or tutorial video automatically or after your approval.

### Can it attach proposals and contracts to a deal?
Yes. It can attach files from your AgentPMT File Manager directly to a deal, contact, or organization, link Google Drive files, and pull existing CRM attachments back into File Manager for review.

### Can it check whether a number can receive texts before sending?
Yes. The phone-number lookup validates a number and can return line type (mobile, landline, VoIP), carrier, and SMS-pumping fraud risk -- so you can avoid wasted sends and risky traffic before spending money.

### Can it download videos or post content?
No. YouTube Discovery returns public metadata only. It does not download audio or video, and it does not create, edit, upload, or moderate content.

### Can it draft replies that match my brand voice?
Yes. Search recent posts about your topic or brand, then have your agent draft on-brand replies for you to review and send — one at a time or in batches.

### Can it handle both leads and deals?
Yes. It manages your Leads Inbox and your deal pipeline, and can convert a qualified lead into a deal — carrying over the linked person, organization, and value.

### Can it help users find the right tool or workflow?
Yes. Search by name or by capability (for example, "send text messages" or "make phone calls") and get pointed to the matching tool, workflow, or agent.

### Can it host conference calls?
Yes. Create named conference rooms, dial participants in, mute, hold, or remove them, and end the room for everyone -- with optional recording.

### Can it host conference calls?
Yes. Your agent can create a named conference room, dial each participant in, mute or remove people as needed, and end the call for everyone when you are done. Recording is optional and can run from the very start of the call.

### Can it keep my pipeline clean and trigger other automations?
Yes. Ask for a pipeline-hygiene report to surface stalled or aging deals, then book follow-ups and update stages in bulk. You can also subscribe webhooks so deal, lead, or activity changes instantly notify the rest of your stack.

### Can it move money or change my account?
No. The connector is strictly read-only. It can read and report your data but cannot send payments, edit records, or change any settings on your Mercury account.

### Can it post images, GIFs, and video?
Yes. Upload media from File Manager or any public URL and attach it to posts, replies, or DMs.

### Can it pull my complete transaction history for reconciliation?
Yes. The connector can page through your full history and return complete results for reconciliation, month-end close, and reporting. Large result sets stay bounded and resumable so nothing times out, and totals are computed exactly and grouped by currency.

### Can it read comments?
Yes. It lists public comment threads on a video or channel, optionally including replies, so you can analyze audience sentiment and recurring questions.

### Can it read my LinkedIn profile?
Yes. It can fetch your name, profile picture, locale, and email when you choose to share it, so your agent can personalize posts and confirm the connected account.

### Can it record and transcribe calls?
Yes. Calls and conference calls can be recorded from the first second, saved with your files, and turned into text transcripts. That gives you meeting notes without a note taker, proof that a notification call happened, and a searchable record of what was said.

### Can it record and transcribe calls?
Yes. Calls and conferences can be recorded from the start, listed and downloaded to the File Manager, and transcribed to text when transcription is enabled -- ideal for QA, proof of notification, and audit trails.

### Can it run an interactive 'press 1 to confirm' phone menu?
Yes. Your agent can run a phone menu that speaks a prompt, waits for the person to press a key or say an answer, and branches based on their choice. When the call wraps up, your agent reads back exactly what was chosen, so a confirmation or approval never gets lost.

### Can it run an interactive 'press 1 to confirm' phone menu?
Yes. Start an IVR call with a directed script of speak, play, and gather steps that accept DTMF digits or speech, then read the caller's exact choices and outcome from the session.

### Can it save files and screenshots for me?
Yes. Screenshots, screen recordings, and any files the page downloads are saved to your File Manager so you can use them in the rest of your workflow.

### Can it send images or PDF attachments?
Yes. MMS supports up to 10 attachments per message, provided as publicly accessible URLs or File Manager file IDs (images, PDFs, and other media).

### Can it show the newest content?
Yes. When recency matters more than relevance, it can list the most recently published AgentPMT content by type.

### Can my agent call me with updates or questions?
Yes. Tell your agent to call you when something important happens or when it needs a decision, and it picks up the phone. It speaks the update in plain language, and if it has a question you can answer by pressing a key or just saying your choice. You get interrupted only when it matters, and the call can be recorded so there is proof of what was said.

### Can my agent create email templates?
Yes. Describe the email you want and your agent creates a reusable dynamic template with placeholders for names, order numbers, and any other data, ready to use for personalized sends immediately.

### Can my agent hold a live, real-time conversation on the phone?
Yes. Start a live ConversationRelay call, stream the caller's speech to your agent as it happens, let the agent use any other AgentPMT tool mid-call, and speak responses back -- with built-in latency telemetry.

### Can my agent hold a live, real-time conversation on the phone?
Yes. Your agent can place a call, greet the person, hear what they say as they say it, and speak back in a natural voice. Mid call it can even use your other tools, like checking an order or booking an appointment, before it responds.

### Can my agent run full marketing campaigns?
Yes. Your agent can build contact lists, add and search contacts, create targeted segments, draft campaign emails, schedule them for the right moment, and report on delivery, opens, and clicks afterward.

### Can my agent send email attachments?
Yes. Attach files from your AgentPMT File Manager or from any public URL. Each email supports up to 10 attachments and 20MB combined.

### Can my agent spend unlimited money?
No. Auto-recharge is optional, off by default, and capped by the max refill count you choose for each rolling 7-day window. If you leave auto-recharge off, agents stop when the balance is exhausted.

### Can the AI agent choose which number it sends from?
No. The outbound sender is fixed by the connected Twilio credential's outgoing number, so agents send only from a number you own and control. This prevents spoofing and keeps your traffic accountable.

### Can the agent choose the caller ID it dials from?
No. The outbound caller ID is fixed by the connected Twilio credential's outgoing number, so agents call only from a number you own. This keeps automated calling accountable and prevents spoofing.

### Can the agent choose the caller ID it dials from?
Every call goes out from the phone number you connect, so the people you call always see your business caller ID. Your agent cannot switch to a different number, which keeps every automated call accountable to a number you own.

### Can the agent see my passwords or cookies?
No. Credentials, cookies, local storage, and profile data stay locked in the background. The agent can only drive the browser and read the page like any visitor would.

### Can the agent see my passwords or cookies?
No. Credentials, cookies, and profile data stay in the background. The agent can only drive the browser and read the page like any visitor would.

### Do I control where the agent can go?
Yes. You set a browsing policy that can restrict the agent to your saved logins only, or allow broader browsing within an allowlist you define.

### Do I need a Pipedrive account, and how do I connect it?
Yes. You connect your own Pipedrive account with a secure one-click authorization. Once connected, your assistant works inside your existing pipelines, stages, and custom fields — there is nothing to export, import, or reconfigure.

### Do I need a Pocket account?
Yes. You connect with a personal Pocket API key from Pocket Settings, Developer, API Keys. The tool works only with your own recordings.

### Do I need a YouTube account or API key?
No. The connection works out of the box with no account linking, API keys, or quota management on your side. Just call it and start discovering data.

### Do I need to approve a direct post?
Yes. post_video requires confirm_user_consent set to true after the creator approves the final video, caption, privacy, interaction settings, commercial disclosures, and AI-generated content labeling.

### Do I need to connect my own LinkedIn account?
Yes. You authorize your LinkedIn account once through a secure connection, and then your agent can post on your behalf whenever you ask. You stay in control and can disconnect at any time.

### Do I need to know how to code?
No. Just describe what you want to add to Minecraft and you'll get back a finished, installable mod file — textures, items, behavior, and all.

### Do I share my password with the agent?
No. The agent uses accounts you've connected; passwords, cookies, and profile data stay in the background and are never exposed to the agent.

### Do I share my password with the agent?
No. The agent uses accounts you have connected, and your passwords, cookies, and profile data stay in the background.

### Do I share my password with the agent?
No. The agent uses accounts you've connected; passwords, cookies, and profile data stay in the background and are never exposed to the agent.

### Do credits expire?
Purchased credits are valid for 12 months from purchase. Free and promotional credits may follow the terms shown when they are granted.

### Do my API keys ever reach the AI agent?
No. The Credential Vault stores every credential encrypted at rest on AgentPMT servers and injects it server-side at the moment the outbound request leaves for the upstream API. The agent sees the endpoint name and the response, never the raw key, token, or password. This is enforced by the connected-API builder: every endpoint must select an injection target (header, body, or query parameter) before it can be saved, and the credential value is bound once and never re-emitted to the agent context or the agent memory.

### Does it cover Mercury Treasury and credit accounts?
Yes. Alongside your operating accounts you can review treasury accounts, treasury statements, treasury transactions, and credit accounts in the same conversation.

### Does it keep version history and can I roll back?
Yes. Every change is recorded with the fields that changed and when. You can review retained revisions and roll back to an earlier version if an edit does not work out.

### Does it manage webhooks?
Yes. You can review your organization's webhook integrations, inspect any one of them, remove stale ones, and send a test delivery to confirm an endpoint is working.

### Does it provide links so agents can cite their sources?
Yes. Results come back with links to the real AgentPMT pages, so agent responses can cite official documentation and content instead of guessing.

### Does it route all of my computer's traffic?
No. Only the browser session's web traffic takes its final hop through the home device you designate as the exit point. The rest of your computer is untouched.

### Does it route all of my computer's traffic?
No. Only the browser session's traffic takes its final hop through the home device you choose as the exit point. The rest of your computer is untouched.

### Does it route all of my computer's traffic?
No. Only the browser session's web traffic takes its final hop through the home device you designate as the exit point. The rest of your computer is untouched.

### Does it search the whole internet?
No. It searches only AgentPMT's own public site and catalog, so answers stay grounded in official AgentPMT resources rather than arbitrary web pages.

### Does it support multiple accounts and currencies?
Yes. It reads every account on your connection, returns available and current balances per account, and reports exact totals grouped by currency so your cash position is always clear.

### Does it support two-factor authentication and one-time passcodes?
Yes. Sending OTP and 2FA codes over SMS is a core use case, and you can pair it with a fraud-risk lookup to block SMS-pumping abuse.

### Does it work across my entire channel or just one video?
Both. You can pull comment threads on a single video or across every video on your channel, including the held-for-review and likely-spam queues that only the channel owner can see.

### Does it work with SendGrid dynamic templates?
Yes. Your agent can browse your templates, pick the right one, and send personalized template email where each recipient receives their own copy with their own data.

### Does it work with autonomous agents and scheduled workflows?
Yes. Every capability is available to agents and workflows, so you can schedule content, automate engagement, and run always-on monitoring.

### Does it work with my custom fields?
Yes. The assistant can discover your custom field names and keys for deals, contacts, organizations, activities, and products, then read and write those fields just like the standard ones.

### Does it work with my existing SendGrid contacts and templates?
Yes. Your agent works with the lists, segments, templates, and senders already in your SendGrid account, and anything it creates shows up in your SendGrid dashboard too.

### Does my agent see my passwords?
No. You save your logins once, and AstroBrowse resumes those sessions for your agent. The agent operates the logged-in browser but never has access to your credentials.

### How are permissions and security handled?
Access follows the permission tier you select when you connect your Mercury account. Because the connector is read-only, it can never move funds. A connection check confirms you are linked and shows your current access tier before any real work begins.

### How do AI agents pay for tools on AgentPMT?
Agents spend USDC from a smart contract controlled budget on Base. Payments are routed through Circle programmable wallets, capped by the budget you set, and visible on chain by transaction hash.

### How do I audit what my agents did?
Every tool call, credential use, payment, and outcome is written to an append-only audit log with correlation IDs. You can search by user, workflow run, agent identity, or transaction hash.

### How do I connect Airtable to AgentPMT?
Enable the Airtable product on a budget, then complete Airtable OAuth from the credentials or product setup flow. Choose the bases (and workspaces) the agent should access. After connect, agents use your grant—not a shared API key—so permissions match your Airtable role.

### How do I connect Asana to AgentPMT?
Enable the Asana product on a budget, then complete Asana OAuth from the credentials or product setup flow. Agents use the connected user's access—not a shared password—so permissions match your Asana membership.

### How do I connect my Mercury account?
Link your Mercury account to the connector and choose the access level you want. Once connected, run a quick connection check and your agent is ready to read balances, transactions, statements, and more.

### How do I connect my X account?
Connect once through secure OAuth. After that, your agents act on your connected account across any workflow.

### How do I handle privacy and compliance requests?
You can redact a message body while keeping the record, or delete the message record entirely, and cancel scheduled messages before they send -- helping you honor deletion requests and retention policies.

### How do I know what something will cost before running?
Marketplace tools and workflows surface credit costs before you run them, and the dashboard shows your current balance, usage history, and refill settings.

### How do I pause a single agent or a whole workflow?
Open the Control Center tab of your dashboard. Agent Guardrails lists every agent with a pause toggle, a spend cap, and a tool allowlist. Workflow Usage lists every active workflow and lets you pause a single workflow without affecting the rest of your fleet. The Wallets tab adds a pause toggle at the wallet level so you can stop outbound payments with a single click. Every pause emits an audit entry and is reversible from the same screen. A paused agent cannot spend credits, call tools, or run workflow steps until you unpause it.

### How do I take over for a CAPTCHA or login?
When the agent hits a step only a human can do, it sends a take-over link to your email and app. You tap the link, handle that one step in the live browser, and the agent continues automatically — no need to watch the session.

### How do I trigger a workflow from outside the AgentPMT dashboard?
Every published workflow exposes a programmatic trigger at POST /api/programmatic/agent-webhooks/{workflowId}/trigger . Send an Authorization: Bearer <token> header and a JSON body with a prompt string. Optionally include your own request_id to carry a correlation id end to end. Triggered runs pick up the same guardrails as dashboard-initiated runs: agent spend caps, tool allowlists, approval gates, and the append-only audit trail in Agent Activity. The response returns the workflow run id so you can poll status or correlate logs in your own system.

### How do my agents and workflows actually use these documents?
You attach a document to an agent or workflow, and its content is provided to the agent as context when it runs. Because agents reference the source document, you maintain the knowledge in one place rather than copying it into every prompt.

### How do statements, invoices, and attachments get delivered?
File outputs such as statement PDFs, invoice PDFs, SAFE documents, and attachments are saved to AgentPMT File Management. Your agent returns a managed file with a secure download link, and the original Mercury-hosted file links are never exposed. You can set how long each file stays available, from one to seven days.

### How does AgentPMT MCP Server Generation work?
Our team takes your existing OpenAPI or Swagger specification, audits the endpoints for agent-safety, and generates an MCP server that wraps your API with credential handling built in. We can deploy the MCP server on infrastructure you control, or on ours, and we hand over auth keys, a runbook, and a rotation playbook. A typical engagement takes a few days from spec handover to live MCP server, plus an optional 30-day support window so your team can onboard without the guesswork.

### How does brand and competitor monitoring work?
Search recent X posts by keyword, hashtag, or account, read your mentions and home timelines, and curate X Lists to watch the accounts that matter to you.

### How does pagination work?
Large result sets come back one page at a time with a page token. Pass that token on your next call to fetch the following page of results.

### How does pagination work?
List workspaces, projects, and project tasks return a next_offset when more pages exist. Pass that value back as offset on the next call. Workspace task search does not support offset continuation.

### How does search work?
Search matches your query against the content of your recordings and transcripts, so you can find a conversation by what was said even when you do not remember its title or date.

### How does the agent sign in without my password?
Glass Browser reuses a session you connected in your dashboard. Your agent resumes that saved login in a real browser, so it never sees, types, or stores your password.

### How does the agent sign in without my password?
Glass Browser reuses the session you connected in your dashboard. Your agent resumes that saved login in a real browser — it never sees, types, or stores your password.

### How does x402Direct keep stablecoin spend inside my limits?
You set caps and reset periods once, and define which digital services your agent is allowed to pay for. The x402Direct smart contract checks every outbound payment against those rules before the transfer clears. A payment that would exceed a cap, or that targets a merchant outside the allowlist, is rejected on-chain with a human-readable reason. Because the rules live in the contract rather than in agent code, changing an agent prompt cannot bypass them. You can update limits at any time from the dashboard, and each change is written to the audit trail with the actor and the new limit.

### How is this different from regular Glass Browser?
Identical browser and controls. Regular Glass Browser exits from the cloud; User IP exits through your home IP. Pick User IP for sites that block cloud traffic. Note that accounts connected here are bound to this product.

### How is this different from regular Glass Browser?
Same browser and the same controls. Regular Glass Browser runs from the cloud, and User IP runs through your own home connection. Pick whichever fits the platforms you work with. Accounts connected here are saved for this product.

### How is this different from writing instructions directly into each agent's prompt?
Inline prompt instructions are duplicated and drift out of sync across agents. Agent Context documents are a single source of truth: one edit propagates to everything that references the document, and every change is versioned and reversible.

### How should agents identify projects and tasks?
Agents should list workspaces, then list projects, then create or list tasks. Use the returned GIDs (opaque Asana IDs) for later updates. Inventing IDs will fail.

### How should agents identify tables and fields?
Agents should discover IDs first: search or list bases, then list tables for a base. Prefer field IDs (they start with fld) when creating or updating records. Inventing base, table, field, or record IDs will fail.

### Is AgentPMT for builders, businesses, or both?
Both. Solo developers ship agent products on top of the infrastructure. Ops, finance, and operations teams delegate operational loops to agents with controls in place. Vendors monetize APIs by listing them as USDC priced tools other agents can call.

### Is each session private and temporary?
Yes. Every task runs in a fresh, single-use browser that is wiped when the session closes, so nothing carries over between jobs.

### Is it safe to let an assistant edit my CRM?
You decide exactly what it can do. Access is read-only by default, and creating, editing, and deleting records are separate permissions you choose to grant. Start with read-only insights and enable writes when you are comfortable — the assistant can never exceed the access you have granted.

### Is it slower than a normal cloud browser?
The browser runs in the cloud for speed; only the last hop uses your connection. Your first session warms up in a few seconds, and the rest are instant.

### Is my Asana data safe with agents?
Access uses your OAuth token and Asana permission model. Revoke the integration in Asana anytime. Prefer least privilege, and confirm before creating many projects or bulk-updating tasks.

### Is my data safe when agents use Airtable?
Access uses your OAuth token and Airtable permission levels. Tokens can be revoked in Airtable integrations at any time. Prefer least-privilege grants (only needed bases) and confirm before destructive schema or bulk delete operations.

### Is there a limit on audio size?
Saving or uploading audio is limited to 100 MB per file. For larger recordings, generate a temporary download link instead.

### Is there a limit on how long a post can be?
Post text can be up to 3,000 characters, which leaves plenty of room for a complete story, a clear call to action, and relevant hashtags.

### Is this suitable for production agents?
Yes. Production teams can combine encrypted credentials, spend controls, optional auto-recharge caps, usage history, and enterprise support for higher-volume use.

### What about Airtable Interfaces?
Agents can list Interfaces and pages, read records from a page, and open a single page record when the path is valid. Page actions only return fields the Interface exposes. To use linked or lookup fields from a page, add those fields to the page layout (and configure detail pages for drill-down when needed).

### What are shared summary templates?
Reusable summary formats your whole team can apply to recordings, so every sales call, interview, or standup is written up in a consistent structure. You can create, edit, and remove them here.

### What aspect ratios are supported?
14 aspect ratios, including 1:1, 16:9, 9:16, 21:9, and 4:5, plus ultra-wide 4:1 and 8:1 banner formats — so a single prompt can produce variants for an omnichannel campaign.

### What can I create?
Items, weapons, tools, and armor; blocks, ores, and crops; custom mobs and bosses; recipes, loot tables, enchantments, and trades; plus biomes, dimensions, and structures.

### What can I do with X / Twitter Automation?
Publish posts and replies, upload images, GIFs, and video, search recent X posts for brand and competitor mentions, read your mentions and timelines, like, repost, and follow, send DMs, and build and manage X Lists — all from agents and automated workflows on a connected X account.

### What can I do with the LinkedIn tool?
You can publish text updates to your LinkedIn feed, share articles and links with a preview card, upload and post images and videos, and read your connected profile. It is designed to keep your professional presence active straight from your AI workflows.

### What can I do with the Pipedrive connection?
Your AI assistant can run your entire sales workflow in Pipedrive: capture and convert leads, create and update deals, contacts, and organizations, move deals through your pipeline stages, schedule calls and activities, log notes, search any record, attach proposals from File Manager, and subscribe webhooks so other tools react to CRM changes — all from plain-language requests.

### What can I search with this tool?
Everything AgentPMT publishes: marketplace tools, workflows, and prebuilt agents, plus documentation, help articles, research papers, videos, and FAQs -- all in one search.

### What can YouTube Discovery do?
It lets your agent search public YouTube videos, channels, and playlists, retrieve detailed video and channel statistics, find trending videos by region and category, browse playlist contents, and read public comment threads. It is a read and research tool for the public side of YouTube.

### What can an agent do in Asana?
Agents can list workspaces and projects, create and update tasks, assign owners, set due dates and completion, add comments, create projects and sections, fetch project status with task counts, and list tasks in a project. Workspace-wide task search may require a paid Asana plan.

### What can an agent do in my Airtable bases?
Agents can list and search bases, inspect table schemas, create and update records, manage fields and tables when allowed, add record comments, and work with Interface pages. They can also set linked-record fields and read lookup values that depend on those links.

### What can it do once it is signed in?
Anything you could do in the browser yourself: post to social media, manage listings on sites with no API, update records in a CRM or ERP, fill forms, upload files, and pull reports from pages behind a login.

### What can my agent do with it?
Anything you could do in the browser yourself: post to social media, manage listings on sites with no API, update records in a CRM or ERP, fill forms, upload files, and pull reports from pages behind a login.

### What can my agent do with it?
Search your recordings by keyword or meaning, open any recording to read its full transcript and AI summary, list recordings by date or tag, create a temporary shareable audio link, save a recording's audio to your files, and upload new audio for Pocket to transcribe.

### What can the agent actually do in the browser?
It can navigate, click, fill and submit forms, select options, extract text and data, upload files, download files, and capture screenshots or full screen recordings of the session.

### What counts as knowledge content?
Documentation, help articles, research papers, videos, and standalone FAQs -- the official material that explains how AgentPMT works and how to get the most from it.

### What data can my agent access?
Accounts and balances, transactions for a single account or across your whole organization, monthly statements, accounts receivable customers and invoices, recipients, treasury and credit accounts, organization details, users, SAFEs, events, webhooks, and pending send-money approval requests.

### What do I connect with?
A Pocket organization API key plus your organization ID. Create the key in Pocket with the scopes you want the tool to use across recordings, templates, and users, each available as read or write.

### What do I get when my mod is finished?
A ready-to-install file you can load straight into Minecraft, preview images of your textures and icons, and editable source files so you can keep customizing.

### What do I need to connect SendGrid?
A SendGrid API key from your own SendGrid account. Create one in your SendGrid dashboard under Settings and API Keys, then paste it into the connection when you add this product.

### What do I need to connect it?
Your Twilio Account SID, Auth Token, and a Twilio phone number to use as your outbound caller ID. All three come straight from your Twilio account dashboard, and connecting takes about a minute.

### What do I need to connect it?
Your Twilio Account SID, Auth Token, and a sending phone number in E.164 format. Add a Messaging Service SID as well if you want to schedule messages.

### What do I need to connect it?
Your Twilio Account SID, Auth Token, and a Twilio phone number in E.164 format to use as the outbound caller ID.

### What do I need to get started?
Just connect your Google account through the secure sign-in flow. Reading public comments works immediately; replying, editing, and moderating use your connected account's permissions.

### What do I need to set up?
Connect a Tailscale Browser Egress credential once — an auth key plus the name of a home device to act as your exit point. After that, your agent's sessions ride your residential IP. See /docs/browser-tailscale-setup.

### What do I need to set up?
Connect a Tailscale Browser Egress credential once — an auth key plus the name of a home device to act as your exit point. After that, your agent's sessions ride your residential IP. See /docs/browser-tailscale-setup.

### What do I need to set up?
Connect a Tailscale Browser Egress credential once, which is an auth key plus the name of a home device to act as your exit point. After that, your agent's sessions run through your own connection. See /docs/browser-tailscale-setup.

### What does Full AI Department Management cover?
Our team handles the full lifecycle: discovery of what the business actually needs, design of workflows and guardrails, build of MCP tools and agents and skill chains, and day-to-day operations including monitoring, tuning, and incident response. You get a monthly review with plain-English outcomes and spend so you can keep stakeholders informed without digging through dashboards. Every engagement starts with a 30-minute discovery call and a short questionnaire. We return a fixed-price statement of work covering deliverables, timeline, and the first operating window.

### What does an agent need to use AgentPMT?
An identity, a budget, a set of allowed tools, and the AgentPMT MCP endpoint. Agents call the Model Context Protocol server and the platform handles authentication, spend tracking, credential vault access, and logging.

### What happens at a two-factor prompt or CAPTCHA?
The agent sends a take-over link to your email or app and pauses, handing you the live browser for up to 10 minutes. You tap the link, complete that one step, and the agent continues the task automatically — so you never have to sit and watch.

### What happens at a two-factor prompt or CAPTCHA?
The agent pauses and hands you the live browser for up to 10 minutes. You complete that one step, and the agent continues the task automatically.

### What happens if I run out?
Runs pause until you manually load more credits or an enabled auto-recharge refill succeeds. Your agents do not keep spending past an empty balance.

### What happens if a site asks me to sign in or pass a bot check?
The agent sends you a link to the live browser. You handle that one step, then the agent picks up where it left off. You do not have to watch the session.

### What happens if a site needs a human, like a CAPTCHA or a verification code?
AstroBrowse sends you a link to take over the live browser for a moment. Once you have handled the step, your agent continues automatically.

### What happens to a paused wallet when an agent tries to spend?
A paused wallet short-circuits every outbound transfer. The x402Direct contract never receives the request, the agent sees a rejected response with a human-readable reason, and the Audit Trail records who paused the wallet, when, and which agent attempted the transfer. Your USDC balance is unchanged. Pausing a wallet takes one click in the Wallets tab. Unpausing takes one click as well. Both actions are reversible and written as append-only audit entries so you can always reconstruct the timeline.

### What is AgentPMT?
AgentPMT is the operating layer for AI agents. It gives agents a persistent identity, a credential vault that proxies API calls so agents never see raw keys, USDC payment budgets enforced on the Base network through Circle programmable wallets, and an append-only audit trail every action lands on.

### What is Pocket Recordings & Transcripts?
It connects your Pocket account to your AI agent so it can search, read, and act on the recordings you capture with Pocket. Pocket is a personal voice recorder and app that turns your conversations, meetings, and calls into transcripts, AI summaries, and action items, and this tool makes that library available inside your workflows.

### What is Pocket Workspace Manager?
It gives your AI agent admin control over your Pocket organization so you can run the workspace without opening the dashboard. Manage recordings, members, invites, shared summary templates, usage analytics, API keys, and webhook integrations directly from your workflows.

### What is an Agent Context document?
It is a reusable, structured piece of knowledge -- a title, optional summary, a Markdown body, and tags -- that your AI agents and workflows load at runtime. Common examples are brand voice guides, standard operating procedures, product and pricing facts, and policy or compliance language.

### What is the Image Generation Agent?
An AI image generator powered by Nano Banana (Google Gemini 3 Flash Image). Create photorealistic product photos, marketing creative, social graphics, icons, concept art, and brand assets from a text prompt, or edit an existing image with reference photos — directly in chat, agents, and workflows.

### What is the Mercury Bank API connector?
It lets your AI agent securely read your Mercury business banking data through the official Mercury API. Your agent can report balances and cash position, search transactions, download statements and invoices, and review treasury, accounts receivable, and operational details, all from a normal conversation.

### What is the difference between Glass Browser and Glass Browser - User IP?
Same browser and the same controls. Glass Browser - User IP routes each session through your own home internet connection, so the activity looks just like your normal browsing. Pick whichever fits the platforms you work with.

### What is the difference between a private document and a public template?
Private documents are yours -- you create and edit them, and only you can modify them. Public templates are admin-curated starting points that anyone can clone into their private library and then customize.

### What is the difference between posting and sending a draft?
post_video publishes to the TikTok profile with the approved privacy and settings. upload_video_draft only sends the video to TikTok so the creator can complete the post in the app.

### What kinds of calls can the AI agent make?
Text-to-speech calls that speak a message aloud, audio-playback calls, interactive IVR menus (press 1 to confirm, etc.), fully custom TwiML call flows, and live two-way AI calls via ConversationRelay.

### What kinds of calls can the AI agent make?
Calls that speak a message in a natural voice, calls that play a recorded audio file, interactive phone menus (press 1 to confirm, press 2 to reschedule), and live two way conversations where your agent listens and responds in real time. It can also set up and record conference calls, and advanced users can define fully custom call flows.

### What makes User IP different?
Every browser session runs through your own home internet connection, so the platforms you use see your normal residential IP. The activity looks just like your own browsing, on your own logged in account.

### What resolutions can I generate?
Choose the tier that fits the job: a low-cost budget draft for ideation, efficient 0.5K and 1K finals, crisp 2K for social and product assets, and 4K for print, ads, and large-format use.

### What sites and accounts can it use?
Any website or account you connect, including social media, CRMs, ERPs, dashboards, and SaaS platforms. It is especially useful for tools that have no API, because it works through the real web interface.

### What video data can I get?
For any public video you can retrieve the title, description, channel, publish date, duration, tags, category, view count, like count, comment count, caption availability, license, and live streaming details, for up to 50 videos in a single call.

### What video formats work?
Use MP4, MOV, or WebM with H.264, H.265, VP8, or VP9, 360-4096 pixel dimensions, 23-60 frames per second, up to 128 MB, and up to 600 seconds.

### What's the difference between Glass Browser and Glass Browser – User IP?
Same browser, same controls. Glass Browser – User IP routes each session's traffic out through your own home internet connection, so sites see your residential IP instead of a datacenter address. Choose User IP for sites that block or challenge cloud and automation traffic.

### What's the difference between Glass Browser and Glass Browser – User IP?
Same browser, same controls. Glass Browser – User IP routes each session's traffic out through your own home internet connection, so sites see your residential IP instead of a datacenter address. Choose User IP for sites that block or challenge cloud and automation traffic.

### When should I use Airtable instead of a spreadsheet export?
Use Airtable when multiple people or tools need a shared, structured system of record with types, links, comments, and Interfaces. Agents can keep that system current from chat—updating statuses, creating rows, and searching live data—without manual CSV round-trips.

### When should I use Asana instead of a plain checklist?
Use Asana when multiple people need shared ownership, due dates, project structure, and status visibility. Agents can keep that board current from chat—creating tasks, assigning owners, and commenting—without manual copy-paste.

### Where do my images go after they're generated?
Every image is auto-saved to AgentPMT File Manager and returned with a download link, file_id, width, height, MIME type, and size — ready to drop into chat, hand to another tool, or use in an automated workflow.

### Where does a TikTok video draft go after upload?
upload_video_draft delivers the video to the creator's TikTok inbox as a notification, not to the profile Drafts folder. Open the TikTok mobile app, check Inbox, and tap the notice to finish caption, privacy, and publishing in TikTok.

### Which HTTP methods can an agent use against a connected API?
You choose the allowed methods per endpoint when you create the connected API: GET, POST, PUT, PATCH, DELETE, or any subset. Requests that use a method outside the allowlist are rejected before the credential is ever attached, so a compromised agent cannot escalate from read to write simply by changing the verb. You can edit the allowlist on a live endpoint at any time from the Secure API Manager. Changes take effect on the next outbound request.

### Which LinkedIn account does it post to?
It posts to the connected member's personal LinkedIn profile, the account you authorize, giving you full control over your professional presence and personal brand.

### Which blockchain wallet does my agent spend from?
AgentPMT provisions a Circle programmable wallet for every customer. You control it with your email and a PIN, and it holds USDC on Base by default. Your agent never holds private keys; it asks AgentPMT to move funds, and AgentPMT checks the request against your x402Direct limits before signing. You can view balance, recent transfers, and per-agent spend from the Wallet tab in the dashboard. Every transfer is recorded on chain and mirrored into the audit trail with the originating agent, the workflow run, and the correlation id.

### Which messaging channels does this support?
SMS, MMS, and WhatsApp. Send plain-text SMS, attach media with MMS, or message customers on WhatsApp -- all from one connected Twilio account.

### Which versions of Minecraft does it support?
Both editions. It builds Bedrock add-ons (.mcaddon) and skin packs (.mcpack) for phones, console, and Windows, plus Java mods for Fabric and NeoForge (.jar).

### Who approves a credit card purchase that my agent requests?
You do, from the AgentPMT mobile app. When an agent requests a credit card purchase, AgentPMT sends a push notification to your phone with the merchant, the item, and the total amount. You confirm with Face ID or fingerprint before the charge executes. Card details never touch the agent. If no approval arrives within the approval window, the purchase is cancelled and the agent receives a declined response. Every approval decision, including timeouts, is written to the audit trail with actor, subject, and outcome.

### Who can see or edit my context documents?
You can only modify your own private documents. Any authenticated user can run every action of the tool, but private documents stay under their owner's control, and only admins manage the shared public templates.

### Who is it built for?
Designers, marketers, e-commerce sellers, content creators, and AI agents that need on-demand, high-quality visuals at any resolution without leaving the conversation.

### Who should use it?
Pocket organization owners, admins, and operations leads who manage a team's recordings, membership, and settings.

### Why are my emails not reaching someone?
Ask your agent to check the address. One suppression check looks across bounces, blocks, spam reports, invalid emails, and unsubscribe lists, explains what it found, and can clear the entry so future sends deliver.

### Why does my agent get blocked without this?
Many sites flag traffic from datacenter and cloud IP ranges and challenge or ban it. Glass Browser – User IP routes the final hop through your home connection, so you appear as a normal residential visitor on your own logged-in session.

### Will it create duplicate contacts or deals?
It searches before it creates. When you ask to add a lead or contact, the assistant first looks for an existing match by email or name, so it links to the right record instead of cluttering your CRM with duplicates.

### Will it hold borderline comments instead of deleting them?
Yes. You can set comments to held-for-review or publish them, giving you a moderation step between 'approve' and 'reject' for anything that needs a closer look.

### Will the agent see every base in my account?
No. Agents only see bases included in the OAuth grant and that your Airtable role can access. If a base is missing, reconnect OAuth and add it under Airtable third-party integrations, or create a new base in a workspace you own.

### Will the agent see every workspace and project?
No. Agents only see workspaces and projects the connected Asana user can access under the OAuth grant. If something is missing, check membership in Asana or reconnect OAuth.

### Can I upload `lakefile.lean`, `lean-toolchain`, or my own build configuration?
No. The platform pins the Lean toolchain and exporter runtime for you. Do not include `lakefile.lean`, `lean-toolchain`, `lake-manifest.json`, or `.lake/` in the uploaded archive.

### Does this compile any Lean program?
No. The selected definition must elaborate to `HeytingLean.LeanCP.CProgramDecl`, which is the exportable LeanCP program form supported by the current compiler path.

### What do I upload to Proof Code Compiler?
Upload a `.zip` whose top-level folder is `UserProofs/` and whose contents are Lean source files only. A single-file project can be as small as `UserProofs/Main.lean`.

### What do `entry_module` and `entry_symbol` mean?
`entry_module` is the Lean module imported from your uploaded source tree, such as `UserProofs.Main`. `entry_symbol` is the definition exported from that module, such as `exportProgram`.

### What is the difference between `fast` and `full` verification?
`fast` checks certificate details and hashes without rebuilding. `full` rebuilds and re-exports under the pinned runtime, then compares the regenerated output with the stored artifact for stronger assurance.

### What should I save after a successful generation?
Save the generated output file, the certificate, the generation log, and especially `artifacts.bundle.file_id`. The bundle is what you need for later verification.

### Which target should I choose?
Use `c` when you want the broadest and lowest-risk support. Use `rust` when you want the same export path with Rust output. Use `wasm` only when you are comfortable with the current target being more constrained than `c`.

## Getting Started

### How do I connect AgentPMT to my LLM?
The easiest way is to download our MCP server and installer. If you are using a cloud agent like ChatGPT or Claude you can install our connector. You can find the instructions here - Integrate Your Agent