Filuta AI
Autonomous planning agents that QA your game around the clock.
About
Filuta AI deploys neurosymbolic planning agents — symbolic planning combined with neural networks, originally developed for autonomous missions — as virtual players that test your game 24/7. You define high-level goals in plain language (reach a location, defeat an enemy), and the agents plan and execute the action sequences themselves, re-planning when the build changes instead of breaking like scripted tests.
The self-maintaining angle is the pitch: tests adapt as the game evolves. Backed by $4.2M in seed funding (Rockaway Ventures, June 2025) with Bohemia Interactive cited as a user. Limitation: integration requires instrumenting the game as a 'digital twin', and as a young startup, engine coverage details are thin.
What it can do
- Goal-driven autonomous test agents
- Self-maintaining tests across builds
- Adaptive exploration for edge cases
- 24/7 continuous testing
- Detailed bug reports with logs
- Plain-language goal definitions
Setup
- Contact Filuta AI for access (filuta.ai/game-qa).
- Instrument your game with their digital-twin data layer.
- Define test goals in plain language.
- Let planning agents run 24/7 and review the bug reports.
Prerequisites
Game build that can be instrumented; Filuta AI account.
Use cases
Works with
Trust score — 5/10
Scored 5/10 (metrics tier, metrics-v1). Evidence: $4.2M seed (Rockaway Ventures, Jun 2025); Bohemia Interactive testimonial; proprietary; requires digital-twin instrumentation; young startup — engine coverage details thin. Manual review: self-maintaining tests are the credible differentiator vs scripted QA. License: Proprietary; contact for access..
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 5.0/10
- Maintenance · recency, releases, issue load
- 6.0/10
- Openness · license + docs
- 3.0/10
- Manual review · sanity read + red-flag check
- 6.0/10
- · $4.2M seed (Rockaway Ventures, Jun 2025); Bohemia Interactive testimonial
- · proprietary; requires digital-twin instrumentation
- · young startup — engine coverage details thin
- · manual review: self-maintaining tests are the credible differentiator vs scripted QA
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.