Before you start
- A DevTune project on a plan that includes API access. No account yet? Let your agent set one up.
- An Eve agent project. These steps add DevTune as a connection the agent can call.
- A project API key from API Keys in the account sidebar. DevTune shows the key once, so copy it when you create it.
Connect with an API key
Your Eve agent connects with a project API key. SetDEVTUNE_API_KEY in the environment of the deployment that runs the agent, then create agent/connections/devtune.ts. The filename becomes the connection name:
Authorization: Bearer <key> on every request. Write the description for the model. The agent searches it when it decides which connection to use.
A key reaches the one project it was created for, with the scopes you gave it. A change made with a key acts as the member who created it.
Check the connection
Ask the agent which DevTune project it is connected to. It finds the tool throughconnection_search and calls devtune__devtune_get_connection_context.
Then ask your Eve agent:
devtune_get_connection_context. If it names the wrong project, connect again and select the right one.
Measure
Ask your Eve agent what AI platforms say and what AI systems fetch from your site:devtune_get_visibility_summary, devtune_get_visibility_diff, devtune_get_competitive_position, devtune_get_top_citation_pages, devtune_get_content_gaps, devtune_get_traffic_summary and devtune_get_404_demand. Measurement windows are 30 or 90 days.
Fix
Ask for the ranked fixes, then work one through:devtune_get_actionslists the queue with its evidence.devtune_change_action_statusaccepts an action, anddevtune_generate_action_briefwrites its brief. Generating a brief spends credits.- Your Eve agent reads the brief with
devtune_get_action_brief. Writing and publishing the page is your work and the agent’s, in your own repository or content system. DevTune drafts and never publishes. devtune_change_action_statuswithmark_liveand the published URL starts the before/after measurement.
Prove
devtune_get_outcomes_ledger returns each measured action as improved, mixed, no clear change, declined, still measuring or unmeasured. Results show what moved after a fix shipped, not what caused it. Results windows are 7, 30, 90 or 365 days.
What needs your approval
- Reading never changes your project or spends credits.
- Accepting an action, changing prompts or competitors, and every other change acts as you. Have the agent say what it will change before it does.
- Briefs, drafts, managed-agent runs, Agent Picks tests and prompt-set analysis spend credits. Approve the spend before the agent starts one.
- DevTune steers suggestions around locked pages and says when it did.
How Eve runs DevTune tools
Eve names the toolsdevtune__<tool>. tools.allow lists the only tools the model can discover. The list above covers the measure, fix and prove steps on this page. The approval policy pauses the agent for a person before it accepts an action, marks one live or generates a brief, and lets the read tools run without a prompt. Add any other tool that changes your project to both lists.
Limits
- The agent can use only the tools in
tools.allow. For a read-only agent, remove the two tools inNEEDS_APPROVALfrom the list. It can then measure, read briefs and read results, and cannot accept an action or generate a brief. - Eve passes a tool’s whole result to the model. Ask DevTune for a narrower window or fewer rows when a result is too large.
- A connection reaches one project. Connect again, or use another key, for a second project.
- Tools your connection has no scope for do not appear in the agent. A connection never gains scopes added later. Edit the key, or disconnect and sign in again.
If something goes wrong
Next steps
- Eve documentation: how Vercel documents connecting outside tools
- MCP server: every tool, its inputs and its scope
- Code mode: two tools in place of the full list, for agents short on context
- API authentication: keys and scopes
- Use DevTune with your agent: setup guides for other agents