get_activity
ChatGPTDaily AI session activity and rate-limit pressure, bucketed into the caller's local days. Use for usage patterns and 'are people hitting limits?'.
Overview
Codiedev Reports answers engineering leaders' questions from their Codiedev reporting, right in the conversation. Ask how engineering is doing this month, whether AI-assisted pull requests actually merge faster, which repositories drive AI spend, how adoption is going on a team, or which models people use and how reliable they are. Who it's for: company admins, CTOs and team managers whose company uses Codiedev to capture AI coding sessions and pull requests. Admins see the whole company and can narrow to any team. Team managers see only their own team and never see spend. Engineers can't connect. What it can do: read delivery and cycle-time stages, the AI-vs-no-AI comparison with its classification coverage, velocity and the throughput forecast, daily activity and rate-limit pressure, adoption and skill reuse, model usage and reliability, capture coverage, and (admins only) spend versus the prior period, ROI, cost per merge, seats and the spend forecast. Limitations: it is read-only and can't change anything in Codiedev. It reports team and company aggregates, not individual session transcripts. Numbers come from stored rollups refreshed about hourly, over 30, 60 or 90-day windows, and only cover sessions Codiedev captured; every answer can quote capture coverage so you know how complete it is. A Codiedev account with the Admin or Team manager role is required.
Tools
get_adoption
ChatGPTAI adoption: who is connected and active (team status), adoption signals, and shared-skill adoption. Use for rollout questions like 'how many engineers are actually using it?'.
get_ai_impact
ChatGPTControlled comparison of merge requests written with AI, touched by AI after opening, and with no captured AI: time from session start to PR, review-to-merge time, self-merge rate, PR size, and the weekly trend. Use for 'is AI actually making us faster?' questions. Includes classification coverage so you can state confidence.
get_automated_runs
ChatGPTScripted and API-driven AI runs (headless reviews, security scans, test runs) as opposed to people's sessions: totals by purpose and source, the daily series, and the pull requests they ran on. Cost is included for admins only. Use for 'how many automated security scans ran last week?' or 'which PRs got automated review?'.
get_capture_coverage
ChatGPTWhat share of started AI sessions were captured. Every other metric undercounts by this much, so quote it when giving confidence in a number.
get_connections
ChatGPTHow many people are invited, joined, have installed Codiedev and are using it, active this week, and the weekly history. Counts only. Use for rollout questions like 'how many people have we onboarded?'.
get_finance
ChatGPTCompany admins only. AI spend for the window versus the prior period, ROI, cost by repository, and proven waste (spend on abandoned work). Use for budget and ROI questions.
get_finance_detail
ChatGPTCompany admins only. One Finance card: cost per merged PR, model savings, a model what-if, seat utilization, or the spend forecast.
get_model_usage
ChatGPTWhich AI models the team uses, request and token mix, and reliability (errors, rate limits). Cost fields are included for admins only.
get_overview
ChatGPTThe headline engineering report for the company and each team: delivery (merged PRs, cycle-time stages), activity, AI adoption, spend (admins only), blockers, people counts, model usage, and skills. Start here for broad questions like 'how is engineering doing this month?'. Use sections to trim the response.
get_practices
ChatGPTThe team's review and testing practices (for example 'every PR gets an AI review') and whether each is being met: the target, how many PRs and people meet it. Use for 'are we actually reviewing every PR?'.
get_throughput_forecast
ChatGPTThe forecast of merged PRs for the coming weeks, with its backtest accuracy and (company-wide) live track record. Use for planning and predictability questions.
get_velocity
ChatGPTVelocity trends: merged PRs and cycle time over time, with repository and team drill-down. Use for 'are we shipping faster or slower?' and 'which repo is slowing down?'.
list_teams
ChatGPTList the teams this user can report on, with their ids and parent team. Use it to resolve a team name the user mentions into the teamId the other tools accept. Also says whether the user is a company admin or a team manager.
search_pull_requests
ChatGPTSearch pull requests and merge requests by text in the title or branch (for example a CVE id or ticket key), state and repository. Use for incident and rollout follow-up: which fixes are still open, where, and whether AI sessions worked on them. Returns up to 50, newest first; windowDays looks back from today (default 90).
Capabilities
Engineering Overview For The Company Or A TeamAi Impact On Cycle Time And ReviewVelocity Trends And Throughput ForecastAi Adoption And Skill ReuseModel Usage And ReliabilityAi Spend, Roi And Cost Per Merge (Admins)
Example Prompts
Click any prompt to copy it.
