Skip to main content

AI testing & review

DidWork

Independent verification for AI agent outcomes

  • Community votes0
  • DR by Ahrefs2 no change since last check

Ahrefs Domain Rating set in type 8 Nov 2026, reset 8 Nov 2026.

DidWork verifies that AI agents have actually completed their tasks by checking results independently before workflows continue, catching errors agents miss.

The story so far

Screenshot of the DidWork homepage
Homepage of DidWork

DidWork provides independent verification for AI agents and the software they run. Instead of letting agents grade their own work, DidWork defines what success means, gathers evidence that outcomes actually happened, and gates workflows on verified results. The platform catches wrong results, stops incomplete work, and blocks false success reports. It works with existing agent tools including Claude Code, Cursor, any MCP host, and GitHub Actions through read-only connections to services like Stripe, GitHub, Linear, and Sentry. Verification runs in production the same way it runs in development, refusing to guess when evidence is uncertain and returning UNKNOWN rather than false positives.

Typeset features

  • Independent outcome verification with VERIFIED, FAILED, or UNKNOWN status
  • First-party adapters for Stripe, GitHub, Linear, Sentry, Resend, and HTTP endpoints
  • MCP integration with Claude Code, Cursor, and any MCP host
  • GitHub Actions required check that fails on unverified claims
  • Audit trail storing claims, evidence, and verdicts separately
  • Capability inspection before agents call tools
  • Read-only credential access with AES-256-GCM encryption
  • Continuous monitoring with watches every 5-10 minutes on Pro plan
  • Evidence retention for 7 days on Hobbyist, 1 year on Pro

Pricing

Pricing model: Freemium

Hobbyist: free forever with 250 checks/month; Pro: $9/month with 2,500 checks/month, $0.01 per extra check

Follow in print. Log in to follow DidWork in print

Want to see what DidWork does next? Follow them for milestones, new products and stories by email.

DidWork metrics

Set in type for didwork.sh: Ahrefs Domain Rating and Majestic link data, with the change since the last edition.
MetricValue
Domain Rating2 no change since last check
Trust Flow1 no change since last check
Citation Flow23 no change since last check
Referring domains14 no change since last check
External backlinks20 no change since last check

Ahrefs Domain Rating set in type 8 Nov 2026, reset 8 Nov 2026. Lead topic: Regional/Asia (1). Majestic set 8 Nov 2026, reset 8 Nov 2026. Link data typeset by Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.

DidWork domain colophon

Read the colophon
From the registry's public RDAP record, checked 8 Nov 2026, 00:50 UTC.
Domain age2 months
Registered
Expires
RegistrarCloudflare, Inc
DNSSECNot signed

Full colophon for didwork.sh

DidWork launch colophon

Measured after DidWork went live on Zivaro Launch on 8 November 2026.

Domain Rating (Ahrefs)
2
First measured 8 Nov 2026
Trust Flow (Majestic)
1
First measured 8 Nov 2026
Referring domains (Majestic)
14
First measured 8 Nov 2026

Day 0 since launch. Next receipt: day 30, 8 Dec 2026. These are measurements, not proof of cause: many things move these numbers. Figures we have not measured are left out.

Biggest gains on Zivaro Launch

Your launch, step by step

Free tips from Zivaro Launch for getting ready, launch day, the week after and what to do next.

Read the launch playbook

Questions and answers

What happens when DidWork can't tell?

DidWork returns UNKNOWN on purpose when a provider is unreachable, a record is not visible, or an outcome is not yet decidable. This is treated as "do not proceed yet" rather than guessing. False verification is the failure mode DidWork optimizes against hardest.

How do agents actually use DidWork?

Agents add the MCP server with one command, then one line in instructions: after any consequential action, call did_verify before reporting success, and proceed only on verified. SDKs and the raw API do the same job for non-agent code.

Does DidWork need write access to my accounts?

Never. Adapters read authoritative state through restricted keys and fine-grained tokens. DidWork proves outcomes but never needs the power to cause them.

What happens at the free tier limit?

Without a payment method, requests past 250/month return 402 and watches pause. No verification is deleted, and everything resumes when billing is set up.

Leave a review for DidWork

No review of DidWork set in type yet. Set the first.

Your rating

Reviews are free to set. None are paid for. Read the proofs

Readers' notes · Reprints · Share the page · Your company in print? Claim it · Report a misprint

More on this profile

DidWork has a free listing. The owner can unlock the full profile with a paid launch for $5:

  • Founder story (locked)
  • Milestones (locked)
  • Demo video (locked)
  • Dofollow website link (locked)

More pages like this

  1. Number 1: White Circle logoWhite Circle

    AI safety and control infrastructure for guardrails, monitoring and red-teaming

    AI testing & review

    DR 42 no change since last check 0 votes. Log in to vote for White Circle in print
  2. Number 2: QuAIA™ logoQuAIA™

    AI agents do the busywork, your team makes the calls

    AI testing & reviewAustria

    DR 0 no change since last check 0 votes. Log in to vote for QuAIA™ in print
  3. Number 3: ProUXAudit logoProUXAudit

    Find UX friction before your users do

    AI testing & reviewEstonia

    DR 2 no change since last check 0 votes. Log in to vote for ProUXAudit in print
  4. Number 4: Woodstitch logoWoodstitch

    Human evaluation for text-to-speech with blinded listening studies

    AI testing & reviewUnited States

    DR 8 no change since last check 0 votes. Log in to vote for Woodstitch in print
Help centre