Vikas Pal

I help startup to build scalable Backend architecture | Backend Engineer | Python | Golang | AWS + GCP | K8S | Docker | DevOps

[Ryan Carter @Grow_withAI]

An Anthropic engineer explains why he earns $350K–$950K:

“I know how to build harnesses.

99% of people still build multi-agent systems manually and wonder why they keep breaking.

I build systems that run loops, use sandboxed tools, and turn yesterday’s logs into new skills.

Same model. 10x more reliable agents that improve while you sleep.”

Opus 5.5 → Agents → Harnesses → Loops → Graphs

In a short workshop, he breaks down how to build one from scratch:

Step 1 → Manage loops, context, and sandboxing through a harness

Step 2 → Separate the brain from the tools to reach the first token 60% faster

Step 3 → Run agents server-side and recover from crashes using logs

Step 4 → Make failures recoverable with retries and replays instead of starting over

Step 5 → Turn past execution logs into new memories so the system gets smarter over time

Anthropic calls this process “dreaming.”

Most developers spend weeks building these systems manually.

This workshop shows you a faster way.

Bookmark this and watch it.

[Shreya @shreyacasmalert]

thank me later https://t.co/iNH3rt1d6g

[Sergi @SergiHernando_]

I'm hiring. (Spain)

You know how to:
- Build AI products with AI
- Build secure cloud infrastructure
- Turn a five-word Slack message into a shipped feature

You treat AI agents as an extension of yourself.
You know how much you don't know, and you keep learning anyway.
You design systems.

Very nice to have:
- You've built native mobile apps
- You've worked with voice interfaces

You believe:
- Code alone has no value, engineering practices have to change, and we're still figuring out how
- An agent is only as good as what it knows about your company: your architecture, your constraints, your users, your market

If this sounds like you, send me a DM.

[Vikas Pal @rohitprotobit]

@ratuldawar18 Pls transfer to me :) I'll double in next 21 days 🤣

[Vikas Pal @rohitprotobit]

@stevecaldwell Lets connect ? https://t.co/y3Q4prmJUK

[Vikas Pal @rohitprotobit]

@johneliveloia Can u connect

[Vikas Pal @rohitprotobit]

@claudesfun Lets goo with claude engineer +++

[Vikas Pal @rohitprotobit]

@OpenHandsDev https://t.co/w7jm81Xmuc
https://t.co/Mci8sc8Xxx

[Vikas Pal @rohitprotobit]

First two PRs got merged with @OpenHandsDev ❤️

More to come.

back to open source :)

[Vikas Pal @rohitprotobit]

@angelacollinshq Hey I’m building soln with agentic ai

[Vikas Pal @rohitprotobit]

If you're a founding or an early engineer working at startup. Would love to connect - starting a series of founding engineers .

[Prasenjit Sarkar @stretchcloud]

Spotify's engineering team cut Claude Code token usage by 90% with a two-model routing approach they call Portal. The mechanism is worth understanding because it's not prompt engineering, it's hard blocks at the architecture level.

Two cheaper "assistant" models handle the tasks that don't need the expensive model: opening files, writing repetitive code, boilerplate. The expensive model only touches novel reasoning. Files over 350 lines get blocked from the expensive model entirely, not suggested away from it, blocked.

They tried rules-as-instructions first. It didn't hold. Engineers (and the model) found ways around soft rules. Hard blocks at the routing layer worked where prompt-level guidance failed.

90% token reduction is a big number. The implication is that most of what people use frontier models for in a coding workflow doesn't actually require frontier-level reasoning. Routing to capability level rather than defaulting to the best model available is a legitimate architecture pattern.

Article is worth reading in full.

https://t.co/4Kd8y24ILo

[Vikas Pal @rohitprotobit]

If you're building/build cool agents that solve real problems DM me. I can help you monetize them and connect you with real customers

[rari🈀 @0xwhrrari]

Anthropic engineer:

"90% of our engineers were already running self-improving loops

Now everyone is building the harness around them"

"Prompting is basically finished"

In just 10 minutes, she builds her complete Claude Code harness live from an empty terminal

Agents → Harness → Loops → Graphs → Self-Improving Systems

Prompting was the old workflow

Harness engineering is the next one

This 10-minute breakdown is worth more than most $1,000 agent engineering courses

Watch it today

Then save the full guide on harness engineering below before everyone catches on ↓

[Vikas Pal @rohitprotobit]

@imDhananjay How much to Hired engineer 😅

[Vikas Pal @rohitprotobit]

Just found out one of my friend works remotely as a Software Dev for a Pakistan-based startup/team…

Blocked him immediately. 🚫

Friendship was good while it lasted. 🙃

[Vikas Pal @rohitprotobit]

@israelajala131 Can you dm me your cv

[Vikas Pal @rohitprotobit]

Looking to Hire a backend intern.. ping me if you're interested and can work with high pace startup env culture

[Vikas Pal @rohitprotobit]

Creating a community for 1% Engineer ....

[Vikas Pal @rohitprotobit]

@devXritesh Hahaha it's like if we can store data in mysql why we need postgres 😄