When Meta's monitoring finds a performance regression, an agent can gather the evidence, investigate the relevant code, and prepare a fix for its owner. The same platform also helps engineers pursue planned optimizations. Each path begins with a specific performance problem and ends with a proposed change for an engineer to assess.
What are Meta's capacity-efficiency agents?
Meta's April 2026 operating account describes one internal agent platform serving two related jobs.
The defensive job responds to a performance regression that has already reached production. The offensive job starts from a proposed optimization, such as reducing CPU use in a known hot function. Both jobs need profiling data, code, documentation, configuration history, examples, and a way to prepare a safe change.
Meta built shared Model Context Protocol tools for those information sources. A tool performs a bounded operation, such as searching code or retrieving an experiment result. Skills encode the reasoning patterns of experienced efficiency engineers, including which tools to call and how to interpret the result.
This combination turns expert knowledge into repeatable task specifications and supplied context. New use cases can reuse the same tools while changing the skill that guides the work.
How does Meta turn a production regression into a pull request?
FBDetect is Meta's internal regression detector. The company says it finds thousands of performance regressions each week and can detect changes as small as 0.005 percent in noisy production data.
Once ordinary detection techniques connect a regression to a code or configuration change, the AI Regression Solver performs three stages:
- Gather the symptoms, affected functions, causative pull request, and exact lines that changed.
- Load mitigation guidance for the codebase, language, and type of regression.
- Prepare a corrective pull request and send it to the author of the original change for review.
The agent does not decide that a production metric moved. A separate measurement system supplies the signal and likely cause. The agent handles investigation and implementation after that evidence exists.
How does Meta turn an optimization idea into code?
On the offensive side, an engineer can choose an efficiency opportunity and request a proposed implementation. The agent gathers the opportunity description, optimization documentation, examples of similar work, relevant functions, and validation criteria. A skill supplies the domain method, such as when memoization is appropriate.
The system then proposes a guarded change, verifies syntax and style, and checks that it addresses the intended opportunity. Meta says the result appears in the engineer's editor and can be applied with one click. That is a different handoff from the defensive path's ready-to-review pull request, so the two should not be described as equally autonomous.
Meta reports that automated diagnosis can compress roughly ten hours of manual investigation into about 30 minutes. This is a company estimate for the described workflow, not an independent time study.
What impact has Meta reported?
Meta says its broader Capacity Efficiency Program has recovered hundreds of megawatts of power. It also says the agent systems for offense and defense contribute to that program and help the team expand into more product areas without matching headcount growth.
The public article does not isolate how many megawatts came from agent-generated changes. It does not publish proposal counts, acceptance or merge rates, false-positive rates, reverted fixes, defect rates, review time, or the distribution behind the ten-hours-to-30-minutes example.
The platform is internal. The article describes its architecture and operating use but does not link a public implementation of the tools, skills, or solver.
How does measurement determine the work?
The work enters through a measured queue. Production detection or a reviewed opportunity defines the target. Shared tools assemble evidence. A reusable skill applies specialist knowledge. The agent prepares a bounded result. Existing review and deployment controls decide what ships.
The measurement system gives the agent a starting point and gives the reviewer a target against which to judge the proposed fix.
What would make the operating impact measurable?
Track the path from a detected problem to a proposed fix, engineer acceptance, and a measured change in production. Investigation time, review time, false alarms, and later regressions show the work required along the way. The resulting record can connect agent work to recovered capacity; the total impact of the broader efficiency program cannot supply that connection on its own.