StartupSeed
Autoheal
A self-improving software factory with evaluator and healer meta-agents.
Autoheal runs always-on cloud agents for SDLC work such as incident response, vulnerability remediation, release readiness and AI coding cost control. Supervisory Evaluator agents score worker output using signals like review comments, CI failures and linked incidents, while Healer agents propose changes to prompts, skills, tools or model choice, test them against historical benchmarks and submit them for engineer approval in Git. Each run gets a fresh sandbox in the customer's cloud with policy checks on every tool call, per-agent budgets and audit trails. It raised a $7.9M seed led by Innovation Endeavors (Sept 2026).
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsAn Evaluator scores worker agents on code-review comments, CI failures and linked incidents, and a Healer proposes changes to agents that perform poorly.[1]
- DocsCan run as SaaS or fully air-gapped in your own cloud, with a fresh sandbox per run, per-agent budgets, approval gates and short-lived scoped credentials.[1]
- DocsThe site lists SOC 2 Type II and ISO 27001 and offers zero data retention.[1]
- DocsNamed enterprise deployments: according to the company, Nomura cut MTTR from 2 hours to 15 minutes in one deployment, and AvidXchange reports root-cause analysis in minutes.[1]
Cons
- DocsEvery performance figure comes from the company or its customers; there is no independent benchmark.[1][2]
- DocsEarly deployments focus on incident response, so it is unproven whether the evaluate-and-heal loop works for other workflows.[1]
- DocsNo public pricing and no self-serve trial; adoption is led by forward-deployed engineers and pitched as a three-week rollout.[1]
- DocsSeed-stage: it raised $7.9M led by Innovation Endeavors in 2026.[1]
- Best for
- Enterprises with heavy incident and vulnerability workloads that want agents that improve from their own review, CI and incident signals.
- Watch out for
- Results are self-reported, so measure your own baseline before the pilot.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Co-founder & CDO
Harness engineering
Co-founder & CEO
Security & sandboxes · Cost & limits
Co-founder & CTO
Harness engineering
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
San Francisco, CA · Est. 2023
Devin, the AI software engineer, and the Windsurf IDE.
Cognition builds Devin, an autonomous AI software engineer that plans and executes engineering tasks end-to-end, and acquired the Windsurf agentic IDE in 2025. One of the defining startups of the coding-agent wave.
~$10.2B valuation (Sep 2025)
San Francisco, CA · Est. 2023
Enterprise-grade evals, data and AI gateway.
Braintrust turns prompts and agent traces into testable datasets and CI, plus an inference gateway — helping teams measure whether harness changes actually improve agent quality.
Sources
Verified Oct 29, 2026