Stop re-explaining the work to your AI agent.
DoTheseTasks turns audit notes and screenshots into a private brief your coding agent pulls one task at a time — so it actually finishes each one instead of skimming 27 tasks and stubbing half of them.
Free to start. No credit card. 1 project ready in under a minute.
$ curl -s dothesetasks.com/x/lp_9f3ax2/next.md
# Group: Mobile layout (2 tasks)
Finish every task in this unit, then request the next one.
---
## Task ID: 412
Fix the oversized hero on mobile. The H1 overflows below 380px and pushes the CTA off-screen. Cap the font scale and keep the primary button above the fold. Done when: CTA visible at 360px with no horizontal scroll.
Task completion URL: dothesetasks.com/x/lp_9f3ax2/tasks/412/completed
---
Next unit URL: dothesetasks.com/x/lp_9f3ax2/next.md
Your agent pulls one unit at a time — not all 27 tasks at once. It builds, calls back, then asks for the next.
Hand an agent 27 tasks and it cuts corners on all of them.
Drop a long list into a chat and the agent writes it all in one pass — skimming the details, stubbing the hard parts, and forgetting the screenshot from three messages ago. Now it says "done," and you're left auditing every change to find what it actually skipped, then sending it back to fix each gap. The agent does the coding. Verifying that it did the right thing — across 27 tasks with no proof of what really shipped — is the problem.
How it works
Capture once. Hand off a URL. Watch it close.
-
01
Capture and enhance
Paste one issue per task and drop the screenshots that prove it. AI Enhance rewrites rough notes into implementation-ready tasks with clear acceptance criteria.
-
02
Group and publish
One click groups related tasks into units of work. Publish to a private brief URL: an index of the whole job plus a feed that serves one unit at a time.
-
03
Agent pulls and closes
Your agent fetches the next unit, builds it, and hits a completion callback — then asks for the next. The brief tracks progress and closes itself when the work lands.
What makes a brief agent-ready.
One unit at a time
The brief is an index plus a next feed. The agent pulls a single task or group, finishes it, and asks for more — so context stays small and nothing gets stubbed.
AI groups related work
One click reads the whole list and clusters similar tasks into units, so related changes ship together instead of scattered.
AI Enhance
Turns a rough note and a screenshot into an implementation-ready task — objective, concrete steps, and a "done when" checklist the agent can verify against.
Addressable task IDs
Every task is a stable ID an agent can reference, complete, and report back against.
Screenshots travel with the work
The image that proves the bug rides inside each unit, so the agent sees exactly what you saw.
Completion callbacks
Agents mark each task done through a callback URL as they go. You verify one task at a time against its acceptance criteria — instead of auditing one giant diff to guess what shipped.
Markdown, HTML, and download-ready
One brief, three formats. Fetch the raw markdown, share the HTML, or download the file.
Bearer-token JSON API
Drive projects, lists, and tasks from your own automations.
Authorization: Bearer ntasks_live_...
Hand the URL to the agent you already use
Pricing
Start free. Upgrade when the loop is working.
Free
$0Enough to test one full agent handoff.
- 1 project, 1 list, 10 tasks
- Private brief URLs
- Markdown and HTML exports
- Completion callbacks
Pro
$28/yearFor repeated audits and active build loops. Includes a 3-day trial.
- More projects, lists, and tasks
- 350 AI credits each period
- Top up 125 more credits for $8 anytime
- Bearer-token JSON API and completion callbacks
Write the brief once. Let the agent build from it.
Your next audit can ship as a URL instead of a conversation.