AI Automation Engineer

Ansh Bharti

I build automation pipelines with real validation, bounded retries, and a human approval gate before anything ships publicly.

See the work Get in touch Resume

Evidence

Not a claim — a case study

One project, examined closely: what it does, the constraints it was built under, and the decisions behind it.

Flagship project

TrendCascade

Takes up to 5 keywords and turns Google Trends, Shopping, and Ads data into locality-level search-volume estimates and an AI-generated ad/inventory strategy report.

A decision that mattered

Chose modeled locality/city search-volume estimates (national Ads volume × relative Trends interest ratio) over no numbers at all — the aggregate is grounded in Google's real Ads volume, but any single locality's or single day's estimate is inferred, not measured.

keywords per test run: 4
end-to-end run time: ~2 min
est. manual research time for equivalent output: ~3 hrs (estimated)

n8n

Google Gemini API

SerpAPI

Read the full case study

More flagship work

Flagship

AI/MLCompleted

ContentEngine

A Telegram-driven pipeline that picks a de-duplicated content angle across 4 niches, writes on-brand copy, generates a photorealistic image and 4 branded slides, and — once approved from Telegram — auto-publishes to Facebook and Instagram via Make.com.

end-to-end run time (idea → 4 rendered slides + caption, ready for approval): ~5 min

Headless Intent-to-Execution Bridge

A zero-trust middleware (Zero-API Action Agent) that turns natural-language requests into deterministic, cryptographically signed actions against legacy and on-premise systems — an LLM only reasons and proposes, a no-LLM policy layer validates, a human approves anything high-risk, and a DMZ-isolated executor is the only thing that ever touches the target system.

LangGraph

n8n

HMAC (payload signing)

How I think

Tradeoffs, not talking points

TrendCascade
Chose modeled locality/city search-volume estimates (national Ads volume × relative Trends interest ratio) over no numbers at all — the aggregate is grounded in Google's real Ads volume, but any single locality's or single day's estimate is inferred, not measured.
ContentEngine
Chose Telegram as the entire control surface instead of a proper dashboard — zero UI to build or host, but every interaction (niche pick, approve, reject) has to be squeezed into button taps and callback_data strings, which is why the Router/Switch layer up front is doing real routing work, not just passing messages through.
Headless Intent-to-Execution Bridge
Chose a deterministic, no-LLM validation step (hand-written Python policy checks) over asking a second model to police the first — new policies have to be coded by hand rather than described in a prompt, but it removes the LLM entirely from the trust boundary around execution.

Want the technical deep dive?

Every flagship project page includes the architecture, the alternatives I ruled out, and what actually broke.

View all work Contact me