← All posts
Harsh Jain

Harsh Jain

Forward Deployed Engineer

7 posts · Insights, Engineering, realfast labs · Writing since Feb 2025

Forward Deployed Engineer at realfast, embedding with customers to ship agents into production. Writes about the engineering reality of making agents work.

Insights|The realfast view

The Hidden Cost of a Round-Trip

An ink illustration: a tethered astronaut holding a code snippet leans toward a red-ringed black hole, while on the right a mound of paper spirals up into a distant point of light

When AI compresses days of execution into hours, the day you lose to a vague email stops being invisible. Seven habits to close an issue in one message instead of three.

By Harsh Jain|Jul 6th 2026|6 min read

Insights|The realfast view

Velocity isn't lines per day. It's knowing which lines matter.

An F1 race car at maximum velocity

The entire production diff was about 15,000 lines — roughly thirty lines per engineer per day. AI's real contribution wasn't writing them. It was comprehension, not codegen.

By Harsh Jain|Jun 30th 2026|6 min read

realfast labs|From the Labs

What We Learned Deploying AI Agents for TASC Outsourcing

TASC Outsourcing AI Agents case study

We built two Agentforce agents for TASC Outsourcing that handled 5,100+ sales interactions and improved their email response rates from 0.33% to 1.93%.

By Harsh Jain|Nov 26th 2025|8 min read

realfast labs|From the Labs

Nobody wants to update tickets. So we automated it

Nobody wants to update tickets. So we automated it

Developers hate updating tickets. Managers hate chasing updates. We use Exo, our internal AI agent, to make the whole problem disappear.

By Harsh Jain|Oct 7th 2025|4 min read

Engineering|From engineering

Peeking inside the Mind of the Machine

Peeking inside the Mind of the Machine

On setting up reporting for Agentforce and why reporting is the heart of AI reliability

By Harsh Jain|Apr 15th 2025|6 min read

Insights|The realfast view

So you think running API calls in a loop makes an agent?

So you think running API calls in a loop makes an agent?

New research reveals that simple AI agents fail at enterprise tasks over a third of the time. And the solution isn't just better models.

By Harsh Jain|Mar 7th 2025|6 min read

realfast labs|From the Labs

4 surprising things we learned testing agents on Agentforce

4 surprising things we learned testing agents on Agentforce

We ran into some unexpected quirks while testing Salesforce agents. Here's what you need to know before starting.

By Harsh Jain|Feb 7th 2025|8 min read