Skip to content
ACAnkit Chatriki
Contact

Applied Math & Operations Research · UC BerkeleyApplied Math & Operations Research
UC Berkeley

Ankit Chatriki

I help solve complex business problems.

  • Demand & supply planning
  • Cost & margin modeling
  • ERP / PLM automation
See my work
ABOUTANKIT CHATRIKI
Ankit Chatriki standing in front of the bronze doors of Doe Library at UC BerkeleyDOE LIBRARYUC BERKELEY
BERKELEY, CACLASS OF 2028

Projects and systems

WHAT I’VE BUILT
Demo previewLOOP
CAL HACKS 13.0 · TOP 20 OUT OF 150 TEAMS

Fern

  1. The problem

    Engineering changes quietly blow up budgets and schedules. Open POs, scrapped inventory, rework and supplier lead times don’t get priced in until after the change is approved.

  2. The solution

    A multi-agent system (Claude Agent SDK, MCP) reads the ECR from PLM, computes the BOM delta, and runs cost, timeline and Monte Carlo lead-time models against ERP data in about 60 seconds. Agents only extract and explain; code computes every number, each tagged with its evidence class.

  3. Real example

    An engineer files a change for a cracked motor-controller bracket. Fern prices it at +$415 per aircraft plus $142K–$156K one time, and flags that the only qualified supplier’s 14-week lead time puts the change on the line 13 weeks late, before the board approves it.

TypeScriptClaude Agent SDKMCPSpacetimeDBBright Data
Read the full story →Watch the demoView on Devpost
Demo previewLOOP
SOLO BUILD

Sutra

  1. The problem

    Independent restaurants run on thin margins, but sales, labor, food cost and inventory live in separate systems, so over-ordering and waste go unnoticed until month-end.

  2. The solution

    A FastAPI and PostgreSQL copilot that runs a Meta Prophet forecasting service on daily POS sales, explodes forecast demand through recipe BOMs (28 menu items to 65 SKUs), and sets reorders and daily prep with EOQ, safety stock, reorder points and a newsvendor model.

  3. Real example

    Demand for the Hot Chicken Slider Duo dropped 36% in 30 days, but the standing order still delivered 288 buns a week against 67 needed. Sutra flagged the 77% surplus, with 154 units four days from expiry, and recommended a promotion and a smaller standing order.

PythonFastAPIMeta ProphetSQLPostgreSQL
Read the full story →Watch the demo

Experience

FROM 2023 TO NOW
  1. Jun 2023

    Pristine Window Service

    Founder & Operator East Bay, CA

    Built a residential service business from door-to-door sales to $40K+ in revenue in 5 weeks, leading an 8-student crew trained in sales and service.

    $40K+REVENUE IN 5 WEEKS
    8STUDENTS ON THE CREW
    A Pristine Window Service crew member cleaning an upper window with a water-fed pole
    WATER-FED POLE
    The Pristine Window Service crew at a client's front door with a window screen and the pure-water system on the porch
    PURE-WATER SYSTEM

    Highlights: Pristine Window Service

    • Led and coached an 8-student crew: set the standard for every job, kept quality consistent, and learned how to get the best out of people my own age.
    • Turned what worked into a playbook, a repeatable onboarding for door-to-door sales and service, so new crew members could sell and deliver to the same standard.
    • Owned the full cycle from first knock to finished job: selling, pricing, scheduling routes and crews, and making sure every booked job was delivered.
    • Learned to run many moving parts at once (sales pipeline, crew schedules, equipment and cash) and reinvested about $4,000 in pure-water gear to take on two- and three-story homes.
  2. Aug 2025
    to Jan 2026

    Atara AI

    Co-Founder & Automation Lead Berkeley, CA

    Co-founded an AI automation company. Our voice agent, Maya, reaches new leads by call and text in under 30 seconds, then qualifies and books them.

    <30 secNEW-LEAD RESPONSE, CALL + TEXT
    1. Lead intake & uploadInstantly via CRM sync, CSV or webhook
    2. AI voice outreach (Maya)Calls and texts in under 30 sec
    3. Qualification & triageCaptures key details, flags hot leads
    4. Automated nurtureMulti-step call, text and email sequences
    5. CRM sync & handoffEverything logged, reported weekly

    Highlights: Atara AI

    • Designed and deployed AI voice agents and automated lead qualification workflows using n8n, REST APIs, and webhooks to streamline SMB operations.
    • Led customer discovery, market research, and GTM planning to identify operational bottlenecks, define buyer requirements, and evaluate pilot opportunities.
  3. Aug 2025
    to Mar 2026

    Trinamix

    AI Solutions Engineering Intern Remote

    Ran live demand-planning and automation demos for enterprise buyers, after mapping their supply-chain and Oracle ERP needs.

    Highlights: Trinamix

    • Mapped enterprise supply-chain problems and Oracle ERP requirements to find where forecasting and automation would pay off.
    • Ran live demos of demand-planning and automation tools for enterprise stakeholders.

Toolkit

  • Forecasting & demand planning
  • Inventory & supply planning
  • Cost & risk modeling
  • SQL & Python
  • Excel & Tableau
  • ERP systems (Oracle, ERPNext)
  • AI agents & automation
  • Customer discovery & GTM

Let's talk

I want to be part of solving complex business operations problems.

Email meLinkedInResume (PDF)

ankitchatriki2006@gmail.com

Ankit Chatriki smiling on the UC Berkeley campus
BERKELEY, CAUC BERKELEY