Software Engineering in the Age of AI

🎟️ Please RSVP here to join-in for this conversation in-person.

Software Engineering in the Age of AI

Topic 1: Engineer the Environment, Not Just the Prompt
Most engineering teams using AI coding tools are stuck in phase two. Phase one was prompt engineering: getting better language out of the model. Phase two was context engineering: curating inputs and integrating AI across the SDLC. Phase two worked. It has also hit a ceiling. Phase three is harness engineering: designing the scaffolding and safety nets that determine what the model builds and whether it is allowed to proceed.

The formula is simple: Agent = Model + Harness.

Most teams optimise the model and accept the default harness. That’s where growth stalls.
This talk examines what a production-grade AI harness looks like across four layers: behavioural contracts that encode your team’s norms; deterministic hooks that enforce them regardless of what the model decides; feedback pipelines that wire quality gates directly into the AI loop; and spec-first workflows that constrain the problem before the model writes a line.

Your engineering judgement doesn’t disappear in an AI-assisted workflow. It gets encoded. That encoding is now the senior engineer’s highest-leverage work.
You’ll leave with a concrete framework for auditing your current harness and knowing exactly what to build next.

ㅤ
Topic 2: The Hourglass-Shaped SDLC
Most software teams still organise delivery around implementation. Estimates are often driven by the expected complexity of the implementation, progress is measured through the development stage, and testing and review wait for the implementation to finish.

That arrangement made sense. Implementation consumed most of the effort needed to turn an idea into working software. Building also forced the design to meet the codebase and change under pressure.

AI changes the balance by reducing the human attention spent on implementation. Work around implementation continues to consume substantial human attention. Teams still define the problem and choose a direction before code is written. After code exists, somebody has to decide whether the result is correct, useful, and safe to release.

If the width of each stage represents its share of human attention, the SDLC starts to look like an hourglass. Adding a faster coding tool to the old workflow accelerates the part already taking less human time, while decisions and evidence continue to set the pace for software delivery.

Software output can then rise faster than confidence, which is why this talk argues for an SDLC organised around decisions before implementation, evidence after implementation, and learning that carries production feedback into the next change.

Meet the Speakers
Karun Japhet
Solution Consultant, Sahaj Software
Karun is an engineer and consultant at Sahaj Software. I work on large-scale systems, architecture, and AI in software development. Most of my time goes into helping teams design systems that hold up as they grow especially as AI becomes part of how we build.

Sujit Kamthe
Solution Consultant, Sahaj Software
Sujit is an engineering leader, software architect and AI practitioner with more than 16 years of experience building distributed systems, cloud platforms and enterprise applications, and building high performing engineering teams. His current work focuses on production-grade agentic AI, cloud-native architecture and AI-assisted software engineering. He writes and speaks about software architecture, engineering practices, developer productivity and the changing role of engineers.

Agenda

• 10:00 AM – 10:15 AM: Entry & Networking
• 10:15 AM – 11:15 AM: Talk 1 – Engineer the Environment, Not Just the Prompt
• 11:15 AM – 11:30 AM: Coffee Break & Networking
• 11:30 AM – 12:30 PM: Talk 2 – The Hourglass-Shaped SDLC
• 12:30 PM onwards: Networking

Entry to the event will close at 10:30 AM.

🎟️ Please RSVP here to join-in for this conversation in-person.