Writing
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review. Notes from building it: approvals, gates, evidence and the record.
Most teams run agents from more than one vendor. Here is how a single project in Deliverd collects what each of them asked, who answered, and which tool and model said it was involved, in one record and one evidence pack.
25 October 2026 · Deliverd Engineering Team · 5 min read
From nothing to an agent that asks a real person before it acts: try it with no account in development mode, then a key, a real approval, the MCP route for AI tools, and a sample project to look at.
25 October 2026 · Deliverd Engineering Team · 4 min read
Microsoft runs your agents. Deliverd decides what they may do, and proves who said yes. Now one setting screens every Copilot Studio agent's tool calls, including the agents your people build tomorrow.
25 October 2026 · Deliverd Engineering Team · 5 min read
Rules shouldn't be the thing that slows a good idea down. Put them at the moment an action happens, only for the actions that matter, and teams get on with the work while compliance knows exactly what was decided and by whom.
24 October 2026 · Deliverd Engineering Team · 5 min read
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.
21 October 2026 · Deliverd Engineering Team · 5 min read
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.
21 October 2026 · Deliverd Engineering Team · 4 min read
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.
20 October 2026 · Deliverd Engineering Team · 5 min read
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.
20 October 2026 · Deliverd Engineering Team · 5 min read
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.
20 October 2026 · Deliverd Engineering Team · 4 min read
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.
18 October 2026 · Deliverd Engineering Team · 3 min read
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.
18 October 2026 · Deliverd Engineering Team · 3 min read
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.
18 October 2026 · Deliverd Engineering Team · 4 min read
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.
17 October 2026 · Deliverd Engineering Team · 5 min read
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.
17 October 2026 · Deliverd Engineering Team · 4 min read
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.
17 October 2026 · Deliverd Engineering Team · 4 min read
A worked example at a fictional EU insurer: an AI assistant that takes first notice of motor claims and routes them. Outside the AI Act's high-risk list, it still owes 24 controls. The insurer's own EIOPA framework, the injuries an eval missed, a policy that says what the AI may do, and a DORA incident.
15 October 2026 · Deliverd Engineering Team · 10 min read
A worked example at a fictional EU bank: an AI assistant that recommends loan decisions, followed from the register through evals, a red team, approvals and a model update to the evidence pack. Why credit work owes so much, and the two moments a release was held back.
14 October 2026 · Deliverd Engineering Team · 8 min read
Deliverd now reads release evidence from Langfuse, LangSmith, Braintrust and W&B Weave. The scores stay in your eval tool, an agent never holds its key, and a person sets the bar the release has to clear. Why we built it that way.
14 October 2026 · Deliverd Engineering Team · 5 min read
Connect your W&B project once, and a build step can name a Weave evaluation and have every score it returned recorded as evidence, with each failed case linked. Read with your organisation's W&B key, never a case's inputs or outputs, and a person sets the bar.
14 October 2026 · Deliverd Engineering Team · 4 min read
Connect a Braintrust project once, and a build step can name an experiment and have its scores recorded as evidence, mapped exactly as a braintrust eval --jsonl report is, so one threshold meets either. Read with your organisation's key and never a case's inputs or outputs.
14 October 2026 · Deliverd Engineering Team · 4 min read
Connect LangSmith once, and a build step can name an experiment, or the prefix it gave evaluate(), and have every evaluator's score recorded as evidence. Read with your organisation's key, in the workspace you connected, and never a run's inputs or outputs.
14 October 2026 · Deliverd Engineering Team · 3 min read
Connect your Langfuse project once, and a build step can name an experiment and have its scores recorded as evidence on a governed task. Deliverd reads it with your organisation's keys, never an item's inputs or outputs, and a person sets the bar.
14 October 2026 · Deliverd Engineering Team · 4 min read
AI tools now make videos as well as pages. A report can now carry one too: it streams and seeks in the browser's own player, a video on its own gets a page written for it, and subtitles come with it. On Team, Business and Enterprise.
12 October 2026 · Dave Reid · 4 min read
Ask your AI to write and publish an article, make it public yourself, and paste one iframe into your site. Updates keep the same address, and an agent can never make anything public. Plus an early-access switch for search indexing.
12 October 2026 · Dave Reid · 3 min read
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.
12 October 2026 · Dave Reid · 5 min read
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.
11 October 2026 · Dave Reid · 11 min read
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.
6 October 2026 · Deliverd Engineering Team · 5 min read
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.
6 October 2026 · Dave Reid · 5 min read
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.
6 October 2026 · Deliverd Engineering Team · 5 min read
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.
28 September 2026 · Dave Reid · 6 min read
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.
28 September 2026 · Dave Reid · 7 min read
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.
18 September 2026 · Dave Reid · 9 min read
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.
12 September 2026 · Deliverd Engineering Team · 6 min read
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.
12 September 2026 · Deliverd Engineering Team · 6 min read
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.
12 September 2026 · Dave Reid · 4 min read
The most common thing people ask us for is not a feature, it is a location: can it be in SharePoint? Why publishing into SharePoint cannot work, why Microsoft's own viewers do not close the gap, what we built instead, and the one part of it we cannot fix.
8 September 2026 · Deliverd Engineering Team · 8 min read
What using Deliverd actually looks like: one paste to connect your AI, then four sentences that cover most of the job. Plus the two things we deliberately kept manual, and the parts that are still clunky.
8 September 2026 · Deliverd Engineering Team · 5 min read
Getting a machine to write a good report became routine. Getting it to the six people who need to read it has not improved since 2010. Four things that break between a finished report and its reader, and why a link that is its own password sits behind all of them.
8 September 2026 · Dave Reid · 6 min read
How we version a living report — restore, pin, and a secret scan on every publish — and how we keep a review comment attached to the passage it was about, even after the wording changes underneath it.
6 September 2026 · Deliverd Engineering Team · 6 min read
What Deliverd is for, why the hard part of AI-generated work starts after the report is written, and a prompt you can paste into Claude Code, Codex or Cursor to connect your AI in one step.
6 September 2026 · Dave Reid · 4 min read
Subscribe with RSS. Deliverd is human-in-the-loop infrastructure for AI agents.