Deliverd Screen llms.txt changelog

https://deliverd.dev/llms.txt

− Tasks are included in Team, Business and Enterprise. A task keeps the goal of a piece− - Claude Code plugin (the MCP server and all 4 skills): claude plugin marketplace add deliverd-dev/deliverd-skills− - update_ai_system: Change an AI system's register entry. An agent cannot lower its risk or retire it.− - get_ai_system: One AI system's register entry and the governed tasks that name it.− The model screen is opt-in: an administrator on Business and Enterprise can switch− - [Your AI already knows how to do the work. Deliverd makes sure it's allowed to.](https://deliverd.dev/blog/allowed-to-act) (2026-10-12): Your agents can already find the record and call the API. What they cannot know is whether they are allowed to. One real workflow, start to finish: check policy, get approval, record evidence, and then your own system does the work.− - [The model does the work. The authority sits outside it.](https://deliverd.dev/blog/authority-sits-outside-the-model) (2026-10-11): Satya Nadella argues that frontier models should be governed like insiders, with identity, least privilege, a record and a brake, all kept outside the model. That is what Deliverd is built for. His principles one by one: what ships today, and what is not ours to solve.− - [What a receipt can prove](https://deliverd.dev/blog/what-a-receipt-can-prove) (2026-10-06): When an agent reports what it did, Deliverd checks it against what was approved. Three levels of receipt, the boundary we cannot see past, and why the evidence pack says what it does not prove.− - [Complex infrastructure. Simple interface.](https://deliverd.dev/blog/complex-infrastructure-simple-interface) (2026-10-06): Deliverd has a new look. One obvious action per screen, one word per status, a serif used sparingly, two colours we changed after measuring them, and a composer that does exactly what it says.− - [Only the apps you recognise](https://deliverd.dev/blog/only-recognised-apps-can-connect) (2026-10-06): A security researcher showed us how a client named "Claude" could ask for access on our real consent screen. What a client cannot fake, what the consent screen now leads with, and a setting that refuses everything else.− - [Jev decides the routine call. A person decides the rest.](https://deliverd.dev/blog/jev-decides-the-routine-call) (2026-09-28): Jev, from TypeSafe, settles the routine call in about a second. What it cannot settle comes back as an escalation with nowhere to go. Deliverd supports Jev: that branch becomes a person, on a page, under your policy.− - [Some requests deserve a second thought](https://deliverd.dev/blog/some-requests-deserve-a-second-thought) (2026-09-28): Most requests an agent sends are routine. A few look routine and are not. Deliverd's ethics rules put the right question in front of whoever decides — and never approve anything themselves.− - [Your agent can act. It still has to ask.](https://deliverd.dev/blog/ask-before-you-act) (2026-09-18): An agent that is not given a way to ask will decide for itself — and will decide in whatever way finishes the task. What OpenAI's misalignment reports actually show, and what to do about it.− - [Running agents against Deliverd](https://deliverd.dev/blog/running-agents-against-deliverd) (2026-09-12): A technical walk through the agent surface: two kinds of principal, what an agent identity can and cannot do, the tools in the order a working loop calls them, how policies hold an agent's publish for approval, and how to run one from CI. With the JSON.− - [From a comment to a version, without the retyping](https://deliverd.dev/blog/from-a-comment-to-a-version) (2026-09-12): How the new feedback loop is built: why images on a comment are served through the report's access check rather than a bucket URL, how a snapshot is taken as the member who asked for it, what goes into a revision brief and why it is recorded, and the three things that are still rough.− - [Say it on the page](https://deliverd.dev/blog/say-it-on-the-page) (2026-09-12): Feedback on a report used to be an email with a screenshot in it. Now a reader selects the passage, adds a picture of what they see, and the conversation stays attached to the report — and when you are ready, one button turns everything that is open into the next version.+ Tasks are included in Team, Business Starter, Business and Enterprise. A task keeps the goal of a piece+ - The compliance skill (open source, MIT): npx skills add deliverd-dev/deliverd-skills --skill compliance+ - Claude Code plugin (the MCP server and all 5 skills): claude plugin marketplace add deliverd-dev/deliverd-skills+ - find_flow: Find the flow you started with an externalId, or null, so a restarted job extends it rather than starting a second.+ - update_ai_system: Change an AI system's register entry. An agent cannot lower its risk or set its status.+ - move_ai_system: Put an AI system's register entry forward for assessment, or withdraw it. Decisions on it are a person's.+ - get_ai_system: One AI system's register entry: its lifecycle status and steps, who answers for it, and the governed tasks that name it.+ - screen_data: Before sending text to an AI model, find the personal data, secrets and confidential terms in it, and whether that model may receive them.+ The model screen is opt-in: an administrator on Business Starter, Business and Enterprise can switch+ - [developers: Deliverd Screen](https://deliverd.dev/docs/developers/screen)+ - [Deliverd Screen: an open-source check before every prompt](https://deliverd.dev/blog/deliverd-screen) (2026-10-21): The detectors behind Deliverd's data screening are now a free, MIT-licensed library for TypeScript, Python and Rust. Find and redact personal data, secrets and your own confidential terms before text goes to a model, on your own machine, with no account.+ - [AI recommends, a person approves: what 900 CEOs said about control](https://deliverd.dev/blog/ai-recommends-a-person-approves) (2026-10-21): A 2026 survey of 900 CEOs found AI informing decisions everywhere, and only one in five letting it act alone. Governance came first on their list of what AI success needs. Here is what the numbers say, and what we built for them.+ - [Check what your agents send to a model, before they send it](https://deliverd.dev/blog/check-what-you-send-to-a-model) (2026-10-20): Data screening finds the personal data, secrets and confidential names in a prompt, checks them against what your AI register approves that model for, and redacts them, asks a person, or refuses. The detectors run where your agent runs, so the text never has to reach us.+ - [Due diligence on your suppliers' AI](https://deliverd.dev/blog/due-diligence-on-your-suppliers-ai) (2026-10-20): Classify a supplier's AI yourself, send the supplier only the questions its class calls for, assess every answer, and have the result signed off by the people its risk tier names, with a date to look at it again.+ - [Your EU AI Act reading, on the record](https://deliverd.dev/blog/eu-ai-act-reading-on-the-record) (2026-10-20): Record whether each AI system is in scope of the EU AI Act, in what role you meet it, and whether it is prohibited or high-risk, in the Act's own order. Deliverd works out the status and the duties that follow, and keeps every reading.+ - [Let an AI agent run your shop, and keep the last word](https://deliverd.dev/blog/let-an-agent-run-your-shop) (2026-10-18): AI agents can already refund orders, change prices and send discount codes on Shopify and Wix stores. Here is how to have them ask a person first, without slowing down the everyday work.+ - [Hoplite's agents can now ask your team](https://deliverd.dev/blog/hoplite-questions-answered-by-people) (2026-10-18): Connect Hoplite to Deliverd and a Hoplite agent's questions reach the people you name in Slack, Teams or email. The first answer goes back to the agent, and the run carries on.+ - [The Pixel Pals found us on MakerMap, and now they want to wave at everyone](https://deliverd.dev/blog/pixel-pals-on-makermap) (2026-10-18): We left the blog unattended and the Pixel Pals took it over. Deliverd has a pin on MakerMap, the map of people building things in public, and the pets have opinions about it. Mostly that every other pin deserves a wave.+ - [Meet the Pixel Pals: serious AI, silly little companions](https://deliverd.dev/blog/meet-the-pixel-pals) (2026-10-17): Deliverd now has resident pixel-art pets. There are six, led by Debug Duck, who is far too sure of himself. They react to what happens around them, never read a word of it, and switch off in one click.+ - [Rust is rewriting the Python stack. Deliverd now speaks Rust too.](https://deliverd.dev/blog/rust-is-rewriting-the-python-stack) (2026-10-17): Python's fastest tools are increasingly written in Rust, from uv and Ruff to Pydantic and Polars. Deliverd now has a Rust SDK on crates.io, so an agent built in Rust can ask a person before it acts, with the same behaviour as our TypeScript and Python SDKs.+ - [Every integration, in one place](https://deliverd.dev/blog/integrations-in-one-place) (2026-10-17): Deliverd's Integrations page puts every AI tool, chat app, framework, pipeline and SDK it works with on one searchable page, with how to connect each one and an honest answer about what is coming next.

https://deliverd.dev/llms.txt

− > Deliverd is the system of record for AI work. AI agents use it to involve people: if an agent needs approval, a decision, some information or human review, Deliverd handles that interaction and sends the result back so the agent can continue. It keeps each job's objective and state, checks policy before an agent acts, can also securely publish AI-generated work when humans need to consume it, and keeps the evidence of who decided what.− ## Publish an HTML file right now− If a person asked you to publish an HTML document to Deliverd, use the first of these that applies to you.− 1. You have the Deliverd MCP tools (publish_report is in your tool list): call publish_report with the HTML. That is all.− 2. You can make an HTTP request — a shell, code execution, or a fetch tool that can POST. No account or key is needed:−    curl -X POST https://deliverd.dev/api/v1/drafts -H "Content-Type: text/html" --data-binary @report.html−    or POST JSON { "html": "...", "title": "..." } to the same address. The response carries a claimUrl. Give it to the person and stop: they sign in, or create a free account, and publish it with one click, private to them until they share it. Nothing is visible to anyone before then. The link works once and lasts 24 hours; documents up to 2 MB. Do not retry or poll.− 3. You can only read web pages: tell the person the one step that connects you, then publish with option 1. In ChatGPT: Turn on developer mode (Settings → Apps → Advanced settings → Developer mode. Custom connectors need a paid ChatGPT plan.); then Add a custom connector with this address: https://deliverd.dev/api/mcp (The connector registers itself and sends you to a screen where you choose the organisation and approve access.). Any other assistant: https://deliverd.dev/connect. Or they can upl− https://deliverd.dev/flow.− - publish_report: Publish HTML to a persistent secure URL, with an audience named in plain English.− - update_report: Publish a new version of an existing report, keeping its URL and audience.− - rename_report: Change a report's title or address; the old address keeps working.− - move_report: File a report into a workspace.− - archive_report: Stop a report's URL serving. Reversible; nothing is deleted.− - unarchive_report: Put an archived report back, at the same URL and audience.− - rollback_report: Serve an earlier version again, without republishing it.− - get_report: Fetch a report's metadata, URL and current version.− - find_reports: Search reports by title or slug.− - list_templates: Reports the organisation offers as starting points.− - share_report: Grant people, teams or groups access to a report.− - revoke_access: Take a report's access away again, from the same audience phrase that granted it.− - send_report: Email a report to a list of addresses, with a covering note. Each gets their own link.− - get_profile: Who this connection belongs to, to tell connected accounts apart.− - list_workspaces: List workspaces, with who can already open a given report.− - list_due_schedules: Recurring reports waiting on this agent.− - create_schedule: Ask an agent for a recurring publish, on a cron cadence.− - update_schedule: Change a schedule's cadence, or turn it on or off.− - delete_schedule: Stop asking for a recurring publish.− - list_report_data: List the datasets a report reads when it is opened.− - update_report_data: Replace a report's live data without publishing a new version.− - delete_report_data: Remove a dataset from a report.− - list_comments: Read reader feedback, with the quoted passage and context.− - list_open_comments: Every open comment thread across the organisation's reports — what needs attention.− - get_report_analytics: Who read a report and when: views, readers, by day and by version.− - get_org_analytics: Readership across every report, including the ones nobody has opened.− - get_revision_brief: The open feedback on a report as one revision prompt, with the readers' screenshots.− - comment_on_report: Comment on a report, anchored to a quoted passage.− - retract_comment: Take back a comment nobody has answered yet.− - resolve_comment: Mark a comment thread resolved.− - resolve_audience: Turn natural-language audience phrases into concrete principals.+ > Deliverd is human-in-the-loop infrastructure for AI agents. When an agent needs a person — for approval, a decision, some information or a review — it makes one call, and Deliverd handles the rest: the page the person answers on, the notifications, who is allowed to answer, and the record. The result comes back so the agent can continue. It works with any agent or tool over MCP, the REST API, the TypeScript and Python SDKs and the CLI; it can check an agent's action against policy, or ask a pe+ The whole integration, in the TypeScript SDK (the Python one reads the same):+     import { deliverd } from "@deliverd/sdk";+     const decision = await deliverd.approve({+       title: "Deploy to production"+     });+     if (decision.approved) await deploy();+ Over MCP the same ask is request_approval, then get_approval until it is+ decided; over REST it is POST https://deliverd.dev/api/v1/approvals, then GET+ https://deliverd.dev/api/v1/approvals/{id}. Every request below has the same three shapes.+ https://deliverd.dev/product/approvals.+ ## Before a consequential action (gates)+ Declare an action with check_gate before you perform it, and branch on the+ answer: allowed, refused, or waiting for a named person. After acting, report+ what ran with record_execution. On governed work, check_governance_gate also+ refuses while controls are outstanding. See https://deliverd.dev/product/gates.+ What a gate does, and what it does not:+ - Approval coordination: Any action Deliverd does not carry out itself — a payment, a deployment, a message. The agent asks before it acts, a rule or a person answers, and the agent acts on the answer. The decision is advisory to the agent's runtime: Deliverd records the question and the answer, and does not see the act.+ - Enforcement: Only where Deliverd itself performs the act. Publishing: publishing policy is applied on the server to every publish and every share, and an agent cannot make a report public. And a staged report release, POST /api/v1/gates/{id}/release, where Deliverd makes the approved version live itself.+ - Execution evidence: Every receipt an agent reports after acting. Each receipt says how much was checked: verified when Deliverd did it, hash_matched when the reported artifact's hash matched the approved one, and reported when it is the agent's word. A receipt whose hash, destination or uses differ from the permission is refused.+ Mediated execution for arbitrary actions, and stronger attestation of what an agent did, are on the roadmap and not built.+ ## Keeping long work on its objective (Tasks)+ Tasks are included in Team, Business and Enterprise. A task keeps the goal of a piece+ of work apart from the conversation doing it. Start one with create_task at the beginning of anything+ substantial; call get_task_context when you resume, after a restart or in a+ different tool, instead of asking the person to re-explain. Branch a separate+ problem with create_side_task and bring its result back with apply_side_task.+ When people need to read the outcome, write the report from get_task_context+ and publish it with the task's taskId; it then shows on the task and comes back+ in its context. Only a person changes the objective. See https://deliverd.dev/product/tasks.+ ## Publish an HTML file right now+ If a person asked you to publish an HTML document to Deliverd, use the first of these that applies to you.+ 1. You have the Deliverd MCP tools (publish_report is in your tool list): call publish_report with the HTML. That is all.+ 2. You can make an HTTP request — a shell, code execution, or a fetch tool that can POST. No account or key is needed:+    curl -X POST https://deliverd.dev/api/v1/drafts -H "Content-Type: text/html" --data-binary @report.html+    or POST JSON { "html": "...", "title": "..." } to the same address. The response carries a claimUrl. Give it to the person and stop: they sign in, or create a free account, and publish it with one click, private to them until they share it. Nothing is visible to anyone before then. The link works once and lasts 24 hours; documents up to 2 MB. Do not retry or poll.+ 3. You can only read web pages: tell the person the one step that connects you, then publish with option 1. In ChatGPT: Turn on developer mode (Settings → Apps → Advanced settings → Developer mode. Custom connectors need a paid ChatGPT plan.); then Add a custom connector with this address: https://deliverd.dev/api/mcp (The connector registers itself and sends you to a screen where you choose the organisation and approve access.). Any other assistant: https://deliverd.dev/connect. Or they can upl+ - Microsoft 365 Copilot, Copilot Studio, Foundry and Agent Framework: https://deliverd.dev/microsoft+ - Inside your own product (a hosted or embedded decision for one approver, and an approver's inbox): https://deliverd.dev/docs/developers/in-your-product+ - cancel_approval: Withdraw an approval you asked for, while it is still undecided.

Showing the first 40 of each.

https://deliverd.dev/llms.txt

− > Deliverd gives AI agents a way to involve people. If an agent needs approval, a decision, some information or human review, Deliverd handles that interaction and sends the result back so the agent can continue. It can also securely publish AI-generated work when humans need to consume it.− - Claude Code plugin (the MCP server and all 3 skills): claude plugin marketplace add deliverd-dev/deliverd-skills− - [for research](https://deliverd.dev/for/research)− - [for brokers](https://deliverd.dev/for/brokers)− - [pricing](https://deliverd.dev/#pricing)+ > Deliverd is the system of record for AI work. AI agents use it to involve people: if an agent needs approval, a decision, some information or human review, Deliverd handles that interaction and sends the result back so the agent can continue. It keeps each job's objective and state, checks policy before an agent acts, can also securely publish AI-generated work when humans need to consume it, and keeps the evidence of who decided what.+ - The tasks skill (open source, MIT): npx skills add deliverd-dev/deliverd-skills --skill tasks+ - Claude Code plugin (the MCP server and all 4 skills): claude plugin marketplace add deliverd-dev/deliverd-skills+ - create_task: Start an objective: what the work is ultimately for, kept apart from the conversation and returned at the top of every context.+ - get_task_context: The objective, where a task stands, its decisions, open questions, side-task results, reports and next action — read instead of the history.+ - list_tasks: The objectives you can see, with status, next action and side-task counts — find work already under way before starting more.+ - get_task: One task in full: objective, state, result, findings, decisions, where it sits and its side tasks.+ - create_governed_task: Start an objective under Compliance Mode: the AI system, purpose, owners, risk, data and oversight, held to the controls they require.+ - govern_task: Put an existing objective under Compliance Mode, with what is known of its governance profile.+ - get_governance_context: A governed task's profile, AI system, controls and their state, evidence, readiness and gate answer.+ - update_governance_profile: Record what was learnt about a governed task. An agent may raise risk or add facts; only a person lowers or clears them.+ - get_required_controls: The governance controls a governed task must satisfy, and what satisfies each.+ - submit_evidence: Record evidence for a governed task and the controls it speaks to; one item may satisfy several.+ - request_control_approval: Put a compliance or deployment approval control to a person through the organisation's approval process.+ - check_governance_gate: Whether governed work may proceed, naming the controls still outstanding. Recorded.+ - get_evidence_pack: The AI governance evidence pack of a governed task, with a digest. Assists audit; certifies nothing.+ - register_ai_system: Add an AI system to the organisation's register so governed tasks can name it.+ - update_ai_system: Change an AI system's register entry. An agent cannot lower its risk or retire it.+ - list_ai_systems: The organisation's register of AI systems.+ - get_ai_system: One AI system's register entry and the governed tasks that name it.+ - get_framework_mapping: How framework requirements map onto governance controls, and how far a governed task's completed controls cover them. Not a compliance verdict.+ - create_custom_framework: Draft the organisation's own governance framework. Applies only once a person publishes and adopts it.+ - check_agent_authority: Whether this agent may take a kind of action on its own, only with a person's approval, or not at all.+ - record_model_change: Record a new provider, model or version for an AI system; every governed task using it is reassessed.+ - trigger_reassessment: Ask for a governed task to be reassessed. Its gate stays closed until a person completes it.+ - report_ai_incident: Report an AI incident against a governed task or AI system. High or critical closes the gate until a person resolves it.+ - get_task_graph: Every side task under an objective, with its status and one-line result, and the links between them.+ - update_task: Update a task's working state — where it stands, open questions, what blocks it, the next action — or its status.+ - create_side_task: Branch a problem out of the main task so the main thread stays on its goal. It starts with a chosen snapshot of the parent.+ - add_finding: Record a work product on a task: hypothesis, test, evidence, conclusion, recommendation or a decision you suggest.+ - complete_task: Finish a task with a structured result: summary, findings, proposed decisions, open questions and the next action.+ - apply_side_task: Carry a finished side task's result into its parent, or keep or discard it, and return to the objective.+ - reopen_task: Reopen a finished task when there is more to do. What it found the first time is kept.+ - cancel_task: Call a task off as abandoned rather than finished. Cancelling an objective cancels its open side tasks.+ - request_decision_approval: Put a decision you suggested to the organisation's approval process; approved confirms it, rejected rejects it.+ ## Keeping long work on its objective (Tasks)+ Tasks are included in Team, Business and Enterprise. A task keeps the goal of a piece+ of work apart from the conversation doing it. Start one with create_task at the beginning of anything+ substantial; call get_task_context when you resume, after a restart or in a+ different tool, instead of asking the person to re-explain. Branch a separate