Baz announced the launch of Baz Planner, a new product designed to help engineering teams eliminate bugs and vulnerabilities earlier in the software development process. The company also announced an additional $9 million in seed funding, bringing its total funding raised to $17 million.
The extended seed round was co-led by existing investors Battery Ventures and boldstart ventures. New investors AFG Partners and Disruptive VC also participated in the round. Baz said the funding will be used to support research across coding agents for engineering work.
Baz Planner acts as a gateway between developers and the codebase. The product automatically routes ideas through dynamic loops that detect, root-cause, patch, and validate vulnerabilities and bugs. It is designed to proactively rewrite coding plans to eliminate classes of issues before they reach production.
The company introduced Baz Planner at AI Engineer World’s Fair. Baz said the product scrutinizes every ad-hoc change against current and future architecture before code is saved. It evaluates model suggestions against a risk matrix, blocks unsafe paths, enforces boundaries, and only allows progression toward production after risk mitigation and approval.
Baz said teams using Baz Planner have reported up to a 65% reduction in downstream rework, measured by the frequency of revert and hotfix pull requests following a merge.
Baz was founded by the team that scaled Palo Alto Networks’ Cloud AppSec business. The company said the same principles that reshaped cloud development — observability, explainability, predictability, and reproducibility — are now needed for AI-generated code.
The company’s flagship product, AI Code Review, helps engineering teams govern and secure AI-generated code through agents that enforce coding standards across product, design, architecture, security, and SRE workflows. Baz said it has more than 100 AI, infrastructure, and cybersecurity customers globally since launching last year.
Baz’s AI Code Review analyzes how new code affects runtime, rather than focusing only on style and correctness. The platform is designed to catch bugs, silent regressions, breaking changes, and security flaws by reviewing code in the context of behavior, requirements, APIs, architecture, production systems, and security.
The company’s purpose-built coding agents include a Spec Reviewer Agent for validating code against product requirements and expected behavior, an Advanced Security Agent for identifying vulnerabilities across infrastructure and application code, an SRE Agent for detecting reliability and performance risks using production telemetry, and a Fixer Agent for applying and validating safe code changes in an isolated runtime.
Baz agents can collect requirements, designs, documentation, execution logs, user comments, and organizational knowledge in one place. They can also be programmed to enforce internal standards, engineering practices, security policies, and domain-specific requirements across software development workflows.
KEY QUOTES:
“Our customers are building the backbone of the new AI stack, and they pushed us to go beyond review and intervene as early as the planning stage, where bugs and vulnerabilities are cheapest to eliminate. Baz exists because they refuse to accept that AI-generated code means blindly accepting risk.”
Guy Eisenkot, Co-Founder and CEO of Baz
“Guy and the Baz team built the code-to-cloud security playbook at Palo Alto Networks, and they are now applying that same rigor to the most pressing challenge in AI-native engineering. As development teams deploy fleets of coding agents, Baz is becoming the super harness that coordinates them, from spec-driven development and UI review to security, quality, reliability and planning, ensuring AI-generated code ships safely and at scale.”
Barak Schoster, Partner at Battery Ventures
“We’re thrilled to double down on Baz. Every other tool reviews code after it’s written. Baz’s Planner intervenes at the planning stage and kills entire classes of bugs and vulnerabilities before the code is ever authored. That’s institutional engineering judgment, codified, and it’s the layer the AI stack has been missing. This team ships with incredible velocity, and they’re just getting started.”
Ed Sim, Founder and General Partner at boldstart ventures
