Challa Ravindranath. I spent 20 years learning how software fails. Now I lead AI teams with one rule: never fail the people who rely on it.

Reliability AI Layer 8people

Work

Four calls.

What I decided, and what it changed.

  1. 01 · Microsoft · Enterprise AI · 2025 to 2026

    Build the agent once. Let it run anywhere.

    I set platform and AI direction for a team of fifteen, and designed the agent harness. As Responsible AI Champion, I let nothing on the AI path ship without provenance and gated writes.

    The call

    I exposed the skills headless, as an API, so the same agent plugs into the tools customers already use. The tool contracts are versioned, and the model only reaches data through them.

    The outcome

    One integration. We don’t rebuild it for each new surface.

    Every write validated. Nothing reaches the data without passing the tool contract.

    One request path Headless
    AssistantChatYour app
    Skills APIHeadless · serverless
    Agent harnessMemory · guardrails · models · tools
    Tool contractvalidated
    Enterprise dataSystem of record

    Same agent, same contract

  2. 02 · Microsoft · 2017 to 2025

    One ID across every boundary.

    One ID, end to end.

    The call

    I put one correlation ID across the front-end / back-end boundary where tickets got lost.

    The outcome

    Support SLA down 60%. And the whole organisation took it as its tracing reference.

  3. 03 · Microsoft · 2017 to 2025

    A text change isn’t a code change.

    Copy moved to the business; developers went back to code.

    The call

    Every text edit on our marketing sites was a pull request, a review and a deployment. I proposed moving content out of the codebase into a CMS, and drove it end to end, from the idea to a partnership with Contentful.

    The outcome

    Business users own their words. A copy change no longer needs a developer.

    Locales through content. A new market isn’t an engineering project any more.

  4. 04 · Roche Diagnostics · 2015 to 2017

    Correctness, on a live clinical line.

    Instruments processing about 1,400 samples an hour, where a flaky failure ships straight to a live diagnostic line.

    The call

    As system integration lead, I owned the merge from component release to the customer’s lab, including deploying and testing the full system on-site at labs across Germany.

    The outcome

    Stable releases across cobas 8100, p 612 / p 512 and p 501 / p 701.

Open source

Built in the open.

Contributor · Microsoft Agent Framework

Since September 2026, this is my work: real AI systems, built in the open and measured on real data. I also advise teams on agents and Responsible AI.

  1. 01Foundations AI PlaybookUnderneath every AI system are old ideas10 families of classic algorithms, mapped onto the AI systems that run on them today.Most people call an LLM API. I wanted to know what happens underneath.315tests that run, across 6 problems25 + 12problems and system designs on the roadmapWeeklya post for each problem, linked to its folderC# · .NET 10 GitHub AI Playbook on GitHub (opens in a new tab)
  2. 02Retrieval RechunkWhere RAG pipelines waste money21.6% of 54,085 real documentation chunks never reached the embedding model. They were copies.Most pipelines re-embed every document on every ingest. You pay again for vectors you already have.47,610chunks a second, with the defaultsNuGetdotnet add package RechunkPIIflagged, masked or blocked before anything is embeddedC# · .NET 8 GitHub Rechunk on GitHub (opens in a new tab)
  3. 03Understanding code TSightWhat your code already knows0 AI model calls. Every number is measured from the code and its git history.Joining a team, you spend days building a map of the codebase in your head. Most of it is already in the code and in git.npmnpm install -g tsight1 clickfrom any number to the files and lines it was counted fromCI--fail-on new-cycle stops a change that adds a dependency loopTypeScript · ts-morph · git GitHub TSight on GitHub (opens in a new tab)
Diagram

Click the diagram to zoom · Esc to close

More on the bench. New repos land here as they ship.All repos on GitHub ↗

Recommendations

In their words.

Joel KatzevmanPrincipal EM, Microsoft

“A thoughtful collaborator who uplifts those around him. His combination of technical depth, adaptability, and natural leadership make him an incredible asset to any team.”

Microsoft · Hyderabad, 2017 – 2026

Alexandru CicortasManaging Director, Emposo

“Technical and business acumen always at the high end, a role model for his peers. A true professional and a true gentleman. Would work with him again without hesitation.”

Nokia · Helsinki, 2010 – 2014

Haresh ChandaniHead of Cloud Engineering, KONE

“Actively driving test automation across both protocol-level messaging and the user interface. Versatility and out-of-the-box thinking, an exceptional knack for identifying critical defects early.”

Nokia → Microsoft · Espoo, 2014 – 2015

01 · Microsoft · Enterprise AI · 2025 to 2026

Building the agent harness

Contracts, not trust.

The problem

An AI agent on an enterprise platform has to touch real business data. One wrong write is an audit problem.

The call

I gave the agent one governed path, from conversation to model to data:

The value

02 · Microsoft · 2017 to 2025

Tracing that became the standard

Built so no one could get it wrong.

The problem

One business operation crossed back-end services, plugins, a data platform and a React front end, with no end-to-end trace. Every team had its own correlation pattern, and support tickets vanished at the front-end / back-end boundary.

The call

I put one correlation ID across that boundary:

The pattern, twice more

The value

60%

The support SLA was cut by 60%, and the whole organisation adopted the approach as its tracing reference.

03 · Microsoft · 2017 to 2025

Taking content out of the codebase

A text change isn’t a code change.

The problem

On the marketing websites, every text edit was a developer change. Copy that a product manager should own went through code, review and deployment. Marketing sites change often, so developer time was going into text, not code.

The call

I proposed the idea of a CMS and drove it end to end:

The value

0

Pull requests for a text change. Developer time went back to code, business users owned their own words, and the marketing sites could change at the speed marketing needs. The real call was seeing that this was never an engineering problem.

04 · Roche Diagnostics · 2015 to 2017

Clinical systems integration

From component release to the customer’s lab.

The problem

An instrument like the cobas p 512 is many components built by separate teams: the control unit, sample supply and module sample buffers. None of them counts until they work as one instrument on a live clinical line.

The call

As system integration lead, I owned the merge, from component release to the customer’s lab:

The value

~1,400

Instruments processing about 1,400 samples an hour, where a flaky failure ships straight to a live diagnostic line. Integration was what made separate components safe to run in a real lab.