How it works
1
Data collection
Queries your agent’s runs, errors, costs, feedback, patterns, and user interactions from the configured period.
2
AI analysis
An analytics agent explores the dataset, comparing the period to the previous one and identifying trends, anomalies, and noteworthy changes.
3
Evidence linking
Every finding is backed by links to the runs, sessions, patterns, and failures that support it.
4
Delivery
Recaps are sent to your subscribed Slack channels and appear as highlights on your overview dashboard.
What is in a recap
Every recap includes:- Metrics comparison — run volume, failure rate, cost, feedback ratio, and other key numbers versus the previous period.
- Trends of interest — spikes in errors, drops in satisfaction, models costing more than they should, latency changes.
- Issues by severity — high, medium, and low priority, each with user quotes and linked runs.
- Topic breakdown — what users are asking about most, with percentages and example prompts.
- Highlights — the wins: improved success rates, efficiency gains, tools performing well.
Cadence
Set recap frequency from the Integrations page or through Slack:Dashboard highlights
Recaps also appear as highlights at the top of the overview dashboard. Click any highlight to drill into:- A written analysis of what changed and why
- The key metrics behind the finding
- Links to the specific failures, runs, sessions, or patterns involved
- Example traces illustrating the trend
Slack delivery
With the Slack integration configured, recaps are delivered automatically to your subscribed channels on your chosen schedule.Limitations
- Recaps analyze production data only.
- Findings are grounded in what The Context Company captures. Dimensions your integration does not attach (for example, missing
tcc.userId) will not appear in per-user breakdowns.
Related
Patterns
Known behaviors referenced in recaps.
Failures
Recurring errors summarized in recaps.
Insight Search
Drill into any recap finding in natural language.
Slack
Deliver recaps to channels.
