Anvit Devadiga | AI Builder | AI Deploy Network

About Anvit

AI engineer building context engines, retrieval systems and testing tools for AI and software development. I built Hebra, a repository-aware context engine for AI coding agents (73.9% target-symbol recall at 8K tokens across 90 held-out bug-fix tasks), and Careo, a stateful differential testing engine that caught 30/30 seeded regressions with zero false alarms. I contribute to open-source AI infrastructure, with merged work in vLLM, Microsoft Semantic Kernel and Cua. Mechanical engineering graduate (University of Mumbai) and LeetCode Biweekly Contest global #1.

Professional profile

Location: Mumbai, India
Time zone: Asia/Calcutta
Work mode: Remote, Hybrid, On-site
Availability: Available Now
Industry experience: 1+ years
Working hours: 10:00 - 19:00
Typical response: Within a few hours
Preferred engagement: Small (individual or single team)
Travel: Occasional travel

Proven on the network

Implementation records and publicly available work, where published.

1 AI Deployment delivered, including 1 publicly identified implementation available to inspect.

What Anvit builds

Implementation domains listed on this profile. Evidence-supported items are identified separately below.

Specialisations

AI Agents

AI Evaluation & Testing

AI Infrastructure & Platforms

Prompt & Context Engineering

RAG & Knowledge Retrieval

Builder-listed deployment types

RAG System

AI Deployments

Real AI implementations demonstrated through evidence.

01 / AI DeploymentPublished record

Hebra: Repository-aware context engine for AI coding agents

Open-source context engine that selects and packs the most relevant code into an AI coding agent's token budget, using SQLite FTS5 retrieval, AST-based code graphs and source provenance. Benchmarked on 120 real bug-fix commits.

Software & SaaS · RAG System

View Deployment

Implementation capabilities

Evidence-supported means linked to a published Deployment or Case Study; other capabilities are Builder declared.

Evidence-supported

RAG System1 record

Builder declared

AI Agents
AI Evaluation & Testing
AI Infrastructure & Platforms
Prompt & Context Engineering
RAG & Knowledge Retrieval

Technology

Technologies listed by the Builder, distinguished by published evidence.

Evidence-supported

No published evidence linked yet.

Builder declared

Claude Code

Industry experience

Published Deployments support the listed counts. Other industries are Builder declared.

Software & SaaS

1 published Deployment

Cloud & Infrastructure Providers

Builder declared

Data & Analytics

Builder declared

Trust & verification

A closer look at how this profile and its evidence are reviewed.

Community Member

Published evidence is reviewed against the AI Deploy Network Evidence Standard.

How verification works

Community

Verified Builder

Independently reviewed by AI Deploy Labs against the platform Evidence Standard.

How this is verifiedWhat the platform has established, and what remains builder-declared.

Identity and organisation: Identity checks confirm that the person presenting this profile controls the account and the professional identifiers attached to it, such as a LinkedIn profile. Organisation membership is confirmed by the organisation, not self-declared by the builder.
AI Deployments: An approved AI Deployment is an implementation record the builder submitted and the platform reviewed against the Evidence Standard before publication. Approval confirms the record is complete, coherent and consistent with the supporting material provided — it is not an audit of the client's systems.
Business outcomes: Outcome figures are recorded by the builder on the deployment or case study that produced them, and are reviewed at publication. Aggregates shown on this profile are calculated from those approved records only.
Evidence: Supporting evidence comes from the records the builder published on this platform: approved AI Deployments, published AI Case Studies, verification outcomes and organisation participation.
Currency: Older evidence continues to count and is never removed. Recency is presented separately through Professional Currency so that current expertise can be assessed alongside historical work.
Traceability: Every figure on this profile can be followed to the record that produced it. Open the linked AI Deployment or AI Case Study to read the outcome exactly as it was reported.

The platform does not independently audit client systems or financial records. How this is verified

Professional record and further evidence

Professional Certifications

Some recognition

Oracle Cloud Infrastructure AI Foundations
Oracle
Issue date not specified

Ready to discuss your AI implementation?

Tell Anvit Devadiga what you are trying to automate and the outcome you need. Your message goes directly to the builder, with a copy kept in your Organisation Workspace.