# Agents that get better every day.

> Product page for Learnings: AISquare turns every agent run into signals, finds what keeps going wrong across the fleet, proposes a fix, and once an expert approves it, every agent follows it from the next run.

- **URL:** https://aisquare.studio/product/learning-layer
- **Audience:** Teams running AI agents in production who want them to improve run after run, with a human approving every change
- **Topics:** Learnings, Learning Layer, continual learning, agent improvement, agentic health, rule failures, redundant rules, cost and speed drift, missing rules, reliability, repair brief, human approval, rulebook, insights API, learnings MCP server, evals

## Learnings

Learnings turns every run into signals, finds what's going wrong across your fleet, and proposes the fix. Approve it once, and every agent follows it from the next run.

## Learnings · Support Studio · Last 30 days

Illustrative. Agentic health 94%, +6 pts this month. 4,212 Runs analyzed. 5 Learnings ready. 12 Rules added.

- Rule failing: Refund policy not cited before approval (7 of 20 runs)

- Redundant: 18 rules never fired in 60 days (adds latency and cost)

- Drift: Cost per run 41% above this agent's baseline (impact high)

- Missing rule: Escalate refunds above the cap to a person (recommended)

- Reliability: Lookup tool timing out on 1 in 12 runs (impact low)

Selected learning: Refund policy not cited before approval. Root cause: The refund policy section isn't in the agent's context. Proposed fix: Add section 4.2 to the agent's context and require a citation. Apply to: This run, This agent, Every agent in the Studio.

## Your agents run faster than anyone can review them.

Your team reviews about 1 in every 100 runs. The other 99, nobody looks at.

Without Learnings: Fixed by hand 3 times. Still comes back. Run #324 knows no more than run #1. 10 mistakes, 3 fixes by hand, Still recurring.

With Learnings: Pattern found at run 7. Approved once. Gone from every agent after. 1 mistake, 1 approval, 0 repeats.

Observability shows you what went wrong. Without Learnings, someone still has to find it, fix it and remember it, run after run.

## Detect. Decide. Deliver.

01 · Detect: Find the patterns one run can't show. Learnings reads every run and groups what keeps going wrong, so you see causes, not alerts.

- Rules that keep failing, with the root cause

- Rules that never fire, adding latency and cost

- Cost and speed drift against each agent's baseline

02 · Decide: Nothing changes until your expert says yes. Each learning comes with evidence and a proposed fix. Your expert chooses what to do and how far it goes.

- Flag, add a rule, change context or send a code fix

- Apply to one run, one agent or every agent in the Studio

- Every decision is attributed and kept on the record

03 · Deliver: The rule applies from the next run. Approved fixes join the rulebook with no retraining or redeploy. Engineering gets a brief it can act on.

- Enforced on the next run, at the scope you chose

- A repair brief for your developer or coding agent

- The same insights over the API and the learnings MCP server

## Governed by design.

- On the record: Every learning, approval and rule change is attributed and kept.

- Human approval: Nothing reaches your agents without an expert's sign-off.

- Your rulebooks: Approved fixes land in the rulebooks you already run.

- Scoped and screened: Learnings stay in your workspace, with sensitive data screened before anything is saved.

## Finding issues is the easy part.

- Dashboards: Show you what went wrong. You still have to read them.

- Issue trackers: Suggest a fix. Someone still has to apply it by hand.

- Learnings: Turns an approved fix into a rule the agent follows from the next run.

## Questions about how agents learn and improve.

- Does Learnings change my agents automatically? No. Learnings proposes fixes. Nothing changes until one of your experts approves, and every approval stays on the record.

- How does a learning become a rule? When a pattern repeats across runs, Learnings proposes a fix with the evidence behind it. Once your expert approves, it joins the rulebook and the agent follows it from the next run, with no retraining.

- What does it watch? Cost, speed, reliability and rule results on every run, compared with each agent's own baseline over 7, 30 and 60 day windows.

- How far can a fix go? You choose: just that run, that agent, or every agent in the Studio.

- How is this different from evals? Evals score outputs. Learnings finds the patterns behind them and turns an approved fix into a rule your agents follow.

- What is agentic health? One score per agent that rolls up rule failures, drift, reliability, redundant rules and missing rules, so you can see at a glance which agents need attention.

- Can a coding agent use it? Yes. Learnings writes a repair brief a developer or coding agent can act on, and the learnings MCP server exposes the same reads to Claude Code, Cursor and any MCP client.

- Is it available on every plan? Learnings is available to all AISquare customers.

## From the blog

- [Human in the Loop: What It Means for AI Agents](https://aisquare.studio/blogs/human-in-the-loop)

## Start your journey with AISquare

Stop making the same fix twelve times.

Connect an agent and let every approved fix make the next run better.

## Links

- [Try for free](https://home.aisquare.studio/signup)
- [Book a demo](https://calendly.com/d/dws4-msf-8jc/aisquare-gtm-team)
- [Read the docs](https://docs.aisquare.studio/docs/govern/remember/)
- [RML and Explainability](https://aisquare.studio/product/reasoning-graph)
- [Policy Engine](https://aisquare.studio/product/policy-gates)
- [Collective Intelligence Graph](https://aisquare.studio/product/collective-intelligence)
- [Human in the Loop: What It Means for AI Agents](https://aisquare.studio/blogs/human-in-the-loop)

---

**Machine-readable AISquare**

- Site index for LLMs: https://aisquare.studio/llms.txt
- Agent instructions (when to use AISquare): https://aisquare.studio/agents.md
- OpenAPI specification: https://aisquare.studio/openapi.json
- MCP endpoint (Streamable HTTP, POST): https://aisquare.studio/mcp
- Sitemap: https://aisquare.studio/sitemap.xml
- Blog feed (RSS, full posts): https://aisquare.studio/blogs/rss.xml
- Any page on this site also serves markdown: append `.md` to its path (the homepage is `/index.md`) or send `Accept: text/markdown`.
