Skip to content
Book a demoStart for free
Start for freeBook a demo

Entelligence Blog

Engineering AI: quality, cost, and what ships.

Practical guides, benchmarks, product learnings, and operating ideas for teams using AI to build software.

Latest

Newest first.

Luna first with Sol on escalation against Sol on every PR: 120 verified bugs to 108, $4.13 to $4.15, 77 percent precision to 86 percentLatestCode Quality & Technical Debt

Let the Cheap Model Decide: Luna-First Code Review Found 12 More Bugs Than GPT-5.6 Sol at the Same Cost

Aditya JhaRead it
GPT-6 Astra Cost 1.6x More Per Verified Bug Than GPT-5.6 SolAnalysisGPT-6 Astra Cost 1.6x More Per Verified Bug Than GPT-5.6 SolAditya JhaHow Engineering Teams Can Actually Budget for AI UsageAI in Software DevelopmentHow Engineering Teams Can Actually Budget for AI UsageAditya JhaHow to Reduce AI Agent Costs Without Sacrificing QualitySoftware Quality AssuranceHow to Reduce AI Agent Costs Without Sacrificing QualityAditya Jha

Archive

Every article, by topic.

Search the archive, or filter it by topic.

Showing 14 of 171 articles

Explore Entelligence

Turn the ideas into a measurable pilot.

Start with one repository or one agent workflow, establish a baseline, and see what changes in quality, spend, or delivery.

SOC 2 Type II · flexible deployment · BYOK

The memory starts the day you connect a repo.

From that day on, every session, review and incident lands in the same index.

Start for freeBook a demo
  • No credit card required
  • No training on customer code
  • Deploy in your cloud, your own keys