# qodo-state-ai-code-quality-2025-report-2025-06-11

## Veille

Qodo - State of AI code quality 2025 - Hallucinations - Context - Developer confidence - Survey report

## Titre Article

State of AI code quality in 2025 - Qodo

## Date

2025-06-11

## URL

https://www.qodo.ai/reports/state-of-ai-code-quality/

## Keywords

AI code quality, AI coding, AI tools, software development, developer productivity, code review, AI testing, hallucinations, contextual understanding, developer confidence, Qodo, GenAI, SDLC, code generation, code integrity

## Authors

Itamar Friedman (Co-founder & CEO, Qodo)

## Ton

**Profile:** Industry research | Institutional publisher voice | Analytical-educational register | Intermediate technical level

Qodo's CEO/founder adopts an industry research report voice balancing market insights with product positioning. The survey methodology (developer trust, hallucinations, context challenges) empirically grounds the observations. Developer-centric language (code quality, SDLC, code generation, integrity) demonstrates domain expertise. Measured, professional tone, typical of publisher-sponsored research (in the style of the GitLab DevOps Report, Stack Overflow Survey). The findings → implications structure naturally positions Qodo's solutions. It targets engineering leaders and CTOs evaluating the AI coding tools landscape, combining real-world insights with a publisher's perspective.

## Pense-betes

- **609 developers** surveyed in 2025
- **82%** use AI daily/weekly, **59%** use 3 or more tools
- **65%** of developers have commits shaped/generated by AI (>25% of production code)
- **78%** report productivity gains, **57%** find their work more enjoyable
- **25%** estimate that **1 in 5 AI suggestions** contains errors (hallucinations)
- **76%** have low confidence shipping AI code without human checks (even with few hallucinations)
- **70%** of those with large productivity gains also report better code quality
- **81%** of fast-moving teams using AI review report quality improvements (vs. 55% without)
- **Context = the #1 factor** in perceived quality and trust
- **65%** of developers say AI misses relevant context during refactoring
- **Confidence Flywheel**: rich context → fewer hallucinations → correct code → confidence → faster delivery → better examples → continuous improvement
- Only **3.8%** experience the ideal Confidence Flywheel
- **61% vs. 27%**: developers using AI for testing are 2x more confident in their test suites

## RésuméDe400mots

The « State of AI Code Quality in 2025 » report by Qodo, based on a survey of **609 developers**, explores the evolving role of AI in software development. It highlights that while AI tools have become mainstream (82% daily/weekly usage, 59% use 3 or more tools), deep trust in their outputs remains elusive. AI tools significantly influence production code: 65% of developers report that at least 25% of their commits are AI-generated or AI-shaped.

**Productivity vs. trust: the paradox**

While 78% report productivity gains and 57% find their work more enjoyable, a major barrier persists: hallucinations. **25% of developers** estimate that one in five AI suggestions contains errors, which weighs heavily on trust and adoption. This prevalence of hallucinations creates low confidence: **76% of developers** facing frequent hallucinations are reluctant to ship AI code without human checks. Even among those with low hallucination rates, a majority (75%) hesitate to merge without manual verification.

**Code quality and AI review: a key catalyst**

Contrary to fears, increased productivity with AI often correlates with better code quality. **70% of developers** reporting substantial productivity gains also report better code quality. AI-powered code review acts as a catalyst: **81% of fast-moving teams** using AI for review report quality improvements, versus 55% without it. This automated validation helps maintain quality standards while accelerating delivery.

**Context: a fundamental factor**

The report identifies **context as the #1 factor** in perceived quality and trust. **65% of developers** report that AI misses relevant context during refactoring, a more frequent problem than hallucinations themselves. Similar issues arise in test generation and code review. Developers overwhelmingly call for "better contextual understanding" from their AI tools. The report argues for persistent, automated context learning across the entire repository, as manual context selection is inefficient and frustrating.

**The Confidence Flywheel**

The report introduces the "Confidence Flywheel": a self-reinforcing cycle where context-rich suggestions reduce hallucinations, leading to correct code, increased developer confidence, faster delivery, and ultimately better examples fed back into the model. Only **3.8%** of developers currently experience this ideal scenario, but they report higher quality gains and greater confidence.

**Testing and confidence**

Developers using AI for testing are **2x more confident** in their test suites (**61% vs. 27%** for non-users), suggesting that full AI integration across the development cycle improves overall confidence.

**Strategic conclusion**

Qodo concludes that unlocking the full business value of generative AI requires bridging the gap between LLM capabilities and proven existing systems, with domain integration being critical. The report calls for an agentic code quality platform providing deep context awareness and integrating AI across the entire development cycle to strengthen code quality and developer confidence. This iterative approach, with technical guardrails, is highly effective but also reveals limits: human technical expertise remains essential to catch AI errors, and agents lack business context.

## GrapheDeConnaissance

- Itamar Friedman —dirige→ Qodo (ORGANISATION, 0.98)
- Qodo —publie→ State of AI Code Quality 2025 (DOCUMENT, 0.99)
- State of AI Code Quality 2025 —est_basé_sur→ sondage de 609 développeurs (CONCEPT, 0.97)
- Confidence Flywheel —est_basé_sur→ contexte (CONCEPT, 0.93)
- State of AI Code Quality 2025 —affirme_que→ le contexte est le facteur n°1 de la qualité et de la confiance (AFFIRMATION, 0.95)
- hallucinations IA —réduit→ confiance des développeurs (CONCEPT, 0.96)
- revue de code IA —améliore→ qualité du code (CONCEPT, 0.94)
- Qodo Merge —permet→ revue de code automatisée (METHODOLOGIE, 0.95)
- Qodo Gen —permet→ génération automatisée de tests (CONCEPT, 0.93)
- tests générés par IA —améliore→ confiance dans les suites de tests (CONCEPT, 0.92)
- contexte —s_oppose_à→ contexte (METHODOLOGIE, 0.88)
- productivité IA —converge_avec→ amélioration de la qualité du code (CONCEPT, 0.91)
- Qodo —remplace→ Codium (ORGANISATION, 0.96)

---
Canonical: https://www.thekb.eu/en/fiches/qodo-state-ai-code-quality-2025-report-2025-06-11/