For Builders connecting coding agents, scripts, or CI to an existing growth workspace

Advanced: connect a coding agent or script

Let a coding agent use your project’s connected data and prepare work for review through the Agent CLI or MCP.

Your first result: A durable agent run and a reviewable change with source references, evidence gaps, and a success measure.

What you need: Requires an accessible project, a dedicated user token, an available CLI or MCP client, connected evidence, and an AI configuration and budget suitable for the run.

Example

Illustrative example · A product team working with a coding agent

Give the agent the evidence and a bounded change to prepare.

What Scout found

Project capability discovery: The project can read connected search evidence and prepare an internal review artifact; external publication is not available through MCP.
Search evidence and page review: People search for installation help, while the target page leads with benefits and leaves the first setup step unclear.

What may be going wrong

A short installation checklist could help visitors reach their first useful result. Confirm the missing step against the actual product before preparing the change.

What Scout prepares

Stage a setup-page change with its source references

Prepare a checklist covering project selection, the first connection, and a verification step. Keep the proposed content, source references, and unresolved questions together in a review artifact.

How to check the result

Completed setup after entering the guide

Record the run ID and reviewed artifact. If the change is approved and shipped through the configured publishing path, measure setup completion over the declared window and retain an inconclusive result when evidence is insufficient.

Illustrative scenario, not a customer result. AI runs use the project's configured resources. Preparing work does not grant permission or capability to publish it.

Connect your agent to the project

The server retains provider credentials, project permissions, approval policy, audit records, memory, and quota tracking. External agents use a dedicated TractionScout user token with access to the intended project.

Before you start

Have a running TractionScout deployment and an accessible project with useful evidence. Review connecting your data sources if the project is new.
Obtain a dedicated user access token and the project ID. Store the token in your local environment or automation's secret configuration.
Use the CLI package or repository checkout provided for your deployment. Public package distribution may not yet be available during pre-release.
Review the project's AI configuration and budget before starting an agent run. Runs consume the project's configured AI resources.

Follow Agent CLI and MCP setup for authentication and installation. With a repository checkout, install from its root:

npm install -g ./agent-cli
tscout --help

The commands below assume TRACTIONSCOUT_API_URL, TRACTIONSCOUT_API_TOKEN, and TRACTIONSCOUT_PROJECT_ID are configured as described in that guide. Keep the token out of prompts and checked-in files.

Discover the project before preparing work

tscout auth:status
tscout integrations:list "$TRACTIONSCOUT_PROJECT_ID"
tscout capabilities:execution "$TRACTIONSCOUT_PROJECT_ID"
tscout analytics:suite "$TRACTIONSCOUT_PROJECT_ID" \
  --page-context overview \
  --run-rollup

Inspect connection freshness, available evidence, and execution capabilities. If a prerequisite is missing, make resolving it the next step. A successful authentication check does not establish that every integration or publishing capability is ready.

When the evidence and budget are suitable, explicitly start a preparation run:

tscout agents:orchestrate "$TRACTIONSCOUT_PROJECT_ID" \
  --prompt "Use the connected evidence to prepare one growth move. Include source references, evidence gaps, the proposed change, a primary metric, guardrails, and an observation window. Stage it for review without publishing or activating it."

The orchestration response provides a durable run_id. Set RUN_ID to that returned value, then inspect the run and queued work:

tscout agents:status "$TRACTIONSCOUT_PROJECT_ID" "$RUN_ID"
tscout actions:list "$TRACTIONSCOUT_PROJECT_ID" --status queued

Review the prepared change

Review the durable run for source references and limitations, then inspect the staged artifact. The prompt's request to stage work is an expression of intent; the server's validation and approval policy still govern execution. Confirm the applicable approval and publishing path before shipping any change.

Use MCP or repeat the workflow deliberately

For a compatible agent client, use the MCP descriptor returned by execution capability discovery. The default mode blocks user-authored staging; review_staging additionally permits supported internal review artifacts. All MCP modes block external execution. Check annotations before calling tools: some reads can incur provider charges or persist evidence.

Before scheduling repeated CLI runs, establish a successful manual run and choose a cadence that matches new evidence. Inspect existing runs and queued work to avoid duplicates. Record the returned run ID, enforce an appropriate budget, and route failed or incomplete runs to an owner.

What a useful first result contains

You should have a durable run, source-aware output, and a reviewable next step, or a specific explanation of the missing evidence preventing one. Measure whether reviewed work reaches completion and its declared outcome; the number of generated actions alone does not show that the workflow is helping.

Explore the synthetic product walkthroughs for a tour of the growth workspace. Live analytics shows real, privacy-preserving aggregate traffic from TractionScout.com. For a more specific starting question, use the signup example, Google clicks example, or ad spending example.