Co-founder and CEO at Bito. 

We build codebase intelligence for AI coding and reviews, so AI tools can reason about real systems instead of guessing. 

Before Bito, I built and scaled companies across multiple markets, including PubMatic (NASDAQ: PUBM). 

Right now, I spend most of my time thinking about AI, software systems, and why understanding codebases matters more than writing code faster.

Amar Goel

Super excited to share our first independent evaluation of Bito’s AI Architect on SWE-Bench Pro.

Working with The Context Lab, we evaluated AI Architect using the same Claude Sonnet 4.5 class agent, the same tools, and the same execution limits. The only difference was system context. 

With AI Architect enabled, the results were clear: 

• Task success rate increased by 39%
• Tasks completed 19.6% faster 
• Tool calls dropped by 25.4% 

All without any additional token or compute overhead.  

We intentionally focused this evaluation on large, real-world codebases with millions of lines of code and hundreds of files, because that’s where today’s coding agents struggle the most without system-level understanding. 

This reinforces our core belief: better outcomes don’t come from bigger models alone, but from giving AI real understanding of the system it’s working in. 

The full SWE-Bench Pro evaluation report is available below. 

Link in the comments.

Bito | Top score on SWE-Bench Pro - Deep codebase intelligence for AI coding and reviews

In 2025, AI-assisted pull requests showed around 1.7× more issues than human-written PRs, even though tests passed and reviews looked clean. This will only go up if we don’t understand the root: 

The reason is fairly straightforward once you look closely.  

AI code gen works with partial views of the codebase. 

It sees files and snippets, but it does not see how state flows across services, where invariants were added after past incidents, or which assumptions are baked into downstream consumers.  

When those relationships are missing, the generated code follows patterns that look reasonable locally and break behavior globally. 

The study pointed out that most of the issues appeared in places reviewers and tests are weakest. 

Conditional paths, retries, rollbacks, and failure handling are rarely exercised fully in unit tests, and PR reviews are scoped to diffs.  

If the system context is incomplete, both humans and tools end up approving code that only works under ideal conditions. 

This is why scaling AI coding tools inside large systems has been harder than demos suggest. Throughput goes up, but system risk quietly accumulates. 

This is the gap Bito’s AI Architect is designed to address.

If you want to learn more, I'd be happy to chat. DMs always open.

AI coding tools feel super cool on side projects, then break as soon as they're inside large, existing, enterprise codebases.  

Custom frameworks, internal conventions, fragmented repos, and years of accumulated constraints change the whole narrative. 

A LinkedIn post by Gergely Orosz from earlier last year captured it well, including a case where a top company rolled out an AI coding tool to thousands of developers and roughly half stopped using it a few months later. 

~50% ! 

The fact that it still feels true today matters, because it points to a structural gap (not a temporary tooling gap).

AI code gen breaks down when the tool cannot model the system, including dependencies, call paths, and the implicit contracts that make production software behave.  

That is where codebase intelligence becomes the difference between a demo and something you can trust in an enterprise. 

Exactly what Bito is building: The AI Architect.

Veracode’s 2025 GenAI code security report states that about 45% of AI-generated code still contains vulnerabilities.

This is one big reason AI-generated code keeps adding security debt. And that number has barely changed even as models have improved.

The underlying reason is straightforward. These models learn from public code, and public code includes a lot of insecure patterns.

When AI code gen is asked to implement common tasks, it often reproduces what it has seen most:

Raw SQL queries instead of parameterized ones.
Hardcoded secrets. Missing validation. And more..

The code compiles, looks reasonable in review, and passes basic tests, while carrying flaws that only surface later.

Security rules live across schemas, data flows, and service boundaries. When AI works without seeing those relationships, it fills gaps by pattern matching. That behavior scales insecure code faster than teams can realistically review it.

We built Bito’s AI Architect. It addresses this by building system intelligence through a knowledge graph of the full codebase, so AI code gen reflects how security actually works across the system.

🎤 This is what a customer has to say about the AI Architect:

"We’ve spent too much time fixing agent-generated code. Now most changes work in one shot because Bito’s AI Architect actually understands our services and APIs. It’s been a huge boost to Cursor."

AI Architect is available via MCP (on-prem coming soon).
We are rolling out demos on a huge scale.
DMs open if you want one.

Anand Chandrasekaran ⚡️

I am helping build Crescendo AI and HiOctave AI (Founder) and Celesta Capital (Managing Partner). Formerly, as Partner @ General Catalyst, I helped establish the India-US investing practice and co-create Crescendo, an early offshoot of the Applied AI rollups practice.

Before that, I was CPO/product leader with an overarching mission of democratizing technology platforms - at Five9, we grew from $120m ARR to over $600m bringing CX to cloud and multiple channels through Covid. At Meta (Messenger Platform), we established and grew ‘people to business’ use cases globally for > 1 billion monthly users. At Bharti Airtel, we transitioned from a voice to a data-first network for 300m subscribers in India. Snapdeal / FreeCharge was a roller coaster experience bringing eCommerce to first time consumers and integrating payments.

I enjoy partnering with commercially minded & product obsessive builders. Was an early investor in 80+ companies since 2016 of which 10 today are valued > $1 billion including Deel, OneCard, NoBroker, Hippocratic, PIPE, Carta, Dealshare etc. and 25 more between $100M-1B including InVideo, Titan MSP, MoEngage, Jeh Aerospace, Monarch Money, Exotel, Orange Health, Tonetag, Beacon.ai, Loop, Two Chairs, Farmart, Smith.ai, Observe.ai etc. Named top seed investor focused on 🇮🇳/🇺🇸 by HURUN India Report 4 years in a row (2022-25). Learned a lot co-founding/building Aeroprise fresh out of Stanford (acq by BMC Software).

I hold an M.S. in Electrical Engg. from Stanford University, and a B.S. from PSG College of Tech, India. Part of Young Global Leader community @ World Economic Forum, Fortune's 40 under 40 etc.

Partner

Anand Chandrasekaran

Managing Partner, Celesta Capital. Founder, Crescendo AI & HiOctave AI || Former Partner @ GC, 80+ seed investments, 10🦄s, Product @ Meta/Airtel/Five9.

No alternative text description for this image

🎙️A discussion with Grace Gong on AI, products, venture investing and more… we covered - 

✅ Company co-creation of Crescendo 
✅ How countries like 🇮🇳 and 🇨🇦 benefit from AI and is it different from 🇺🇸
✅ Investing approaches and Celesta Capital focus on Deep Tech 
✅ My favorite - honing a craft over time!

Thank you Paddy PADMANABHAN and the INSEAD team for featuring Crescendo’s unique Creation story as a business school case study. 

Andy’s incredible 20+ year journey @ Alorica also featured here created the right foundation to take advantage of the unique AI moment we saw in 2023!

Hope this helps many students create such ambitious and long-term value oriented newcos across sectors! 🙏 

General Catalyst | Celesta Capital

That's a wrap. The story of Alorica - a billion dollar+ giant in the Customer Experience (CX) and Business Process Outsourcing space built from scratch by Andy Lee and his team. Then comes November 2022 and LLM's and a holy **** moment for the entire industry. Then comes Crescendo.AI - a start-up built from scratch by Andy Lee and Anand Chandrasekaran and their team.  They showcase the #Phoenix Attitude and underscoring the point that disruption is an opportunity to dream and re-imagine new and better ways of creating value for all stakeholders. 

The Phoenix Encounter Method Andy Lee Anand Chandrasekaran Bala Vissa Indira Pant INSEAD

https://lnkd.in/gdBYCBJb

https://lnkd.in/gXqPdir8

Anand Chandrasekaran is the Managing Partner of Celesta Capital 

Prior to joining Celesta, Anand Chandrasekaran co-founded and was President of Crescendo, an AI-first contact center business, co-created and backed by General Catalyst (GC). He is a former Partner and Venture Advisor at GC. Earlier in his career he was CPO and a product leader for two decades at Five9, Meta (Messenger), Bharti Airtel, Snapdeal (FreeCharge), and Founder of Aeroprise (acquired by BMC Software). He was recognized as the #1 seed investor focused on the India – U.S. corridor by the HURUN India Report three years in a row from 2022-2024. Anand holds an M.S. in Electrical Engineering from Stanford University, and a B.S. from PSG College of Technology, India. In 2010, Anand was named Young Global Leader by the World Economic Forum. In 2017 and 2018, he was named to Fortune's 40 under 40 India list.

Topics: 

- Why the best AI investors think like product leaders
- How to build truly cross-border teams
- How enterprises decide when AI is “production-ready”

#AI #VentureCapital #EnterpriseAI #ProductLedGrowth #OperatorToInvestor #IndiaUSTech #SeedStage #StartupInvesting #B2BTech #SmartVenture

Anand Chandrasekaran, Celesta MP on AI-First Companies & Product DNA

taplio

The Battle

Amar Goel

Anand Chandrasekaran ⚡️

Followers

Posts

Engagements

Likes

Performance ScoreAmar Goel's LinkedIn Performance

Performance ScoreAnand Chandrasekaran ⚡️'s LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Amar Goel

Anand Chandrasekaran ⚡️

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Amar Goel's LinkedIn Performance

Performance ScoreAnand Chandrasekaran ⚡️'s LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreAmar Goel's LinkedIn Performance