> Markdown version of [/videos/100278-designing-for-agents-will-make-you-better-at-designing-for-humans?t=482](https://www.wearedevelopers.com/videos/100278-designing-for-agents-will-make-you-better-at-designing-for-humans?t=482). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Designing for Agents Will Make You Better at Designing for Humans

Optimizing your architecture for AI agents directly accelerates workflows for human developers. Discover how embracing Agent Experience (AX) elevates engineers from implementers into platform architects.

- **Speakers:** [Dana Lawson](https://www.wearedevelopers.com/@dana-lawson)
- **Event:** World Congress 2026 Europe
- **Published:** July 10, 2026
- **Duration:** 32:14
- **URL:** https://www.wearedevelopers.com/videos/100278-designing-for-agents-will-make-you-better-at-designing-for-humans

## Summary

The software development lifecycle is quietly being rewritten by coding agents, fundamentally expanding the "builder persona" from traditional engineers to anyone with a vision and intent. Designing software platforms to natively accommodate these AI workflows—a discipline known as Agent Experience (AX)—does not come at the expense of human users. In fact, optimizing systems for machines directly accelerates and clarifies the process for humans. The exact same machine-readable logs and structured error codes that teach an agent how to fix a bug allow a senior engineer to identify a failed build entirely at a glance.

To make this paradigm a reality, organizations must rethink traditional architectures. Legacy, pull-based REST API endpoints designed for sequential human handoffs must evolve into capability-based, event-driven pipelines. When infrastructure emits continuous event streams (like build failures or deployment starts), agents can diagnose, test, and attempt fixes autonomously. Additionally, complex distributed systems running on tribal knowledge must be codified into "Blueprints"—context-rich architectural records that give agents a deep understanding of cross-service contracts before they touch the plumbing.

Ultimately, this shift elevates traditional software engineers from feature implementers into platform builders and "architects of trust." Because empowering non-technical builders means removing historical guardrails, establishing rigorous safety mechanics is no longer optional. Sandboxed execution environments, transparent audit logging, instant rollbacks, and "human-in-the-loop" approval structures ensure this democratization happens securely. By fully embracing AX as part of human experience, tools amplify judgment and creativity, lowering the barriers to entry for software creation.

**Keywords:** agent experience, coding agents, software development lifecycle, capability-based apis, event-driven architecture, structured error logging, human-in-the-loop deployment, developer experience, autonomous development loops, legacy system modernization, infrastructure sandboxing, platform engineering guardrails, machine-readable endpoints, polyglot distributed systems, automated deployment workflows

## Chapters

1. **Expanding the software builder persona through conversational AI** (01:53) — Programming through natural language allows non-developers to create working applications using intent rather than code syntax.
1. **Removing human assumptions to improve the agent experience** (04:34) — Removing legacy platform assumptions like explicit version control steps allows agents to deploy directly while implicitly improving the human developer experience.
1. **The convergence of user and developer experience** (08:02) — Designing systems for seamless human-agent collaboration requires rethinking the entire application stack instead of simply bolting on agent-friendly APIs.
1. **Shifting the development lifecycle from specifications to intent** (10:22) — Software creation transforms from executing rigid technical specifications into feeding direct problem descriptions and intentions into agent workflows.
1. **Moving from sequential handoffs to shared creation pipelines** (11:21) — Product development becomes a collaborative ecosystem where agents handle continuous testing and deployment alongside human designers and engineers.
1. **Transitioning to autonomous agent development loops** (12:16) — Delivery pipelines evolve into autonomous feedback loops where coding agents independently diagnose and resolve failing builds using machine-readable logs.
1. **Adapting legacy system architectures for agent autonomy** (14:25) — Fragmented services should shift to intent-level capabilities, event-driven triggers, and explicitly documented cross-service contracts to improve agent reasoning.
1. **Establishing trust and security guardrails for autonomous agents** (19:16) — Granting autonomous execution power requires strictly isolated sandbox environments, default human approval checkpoints, and instant rollback mechanisms.
1. **The organizational shift toward platform engineering** (20:32) — As agents handle routine code generation, engineers will transition into platform architects who design safe, company-wide app creation environments.
1. **Actionable steps for improving the agent experience** (21:32) — Teams can immediately modernize their deployment infrastructure by adopting structured error events, event-driven streams, and standardized system blueprints.
1. **Audience Q&A on agent integration and system safety** (26:26) — Discussion covers the shifting skills required for future developers and practical methods for managing mission-critical human oversight.

## Related Moments

- [The evolving role of software engineers alongside agents](https://www.wearedevelopers.com/videos/100132-the-agent-interface-layer-protocols-tools-and-trust-boundaries) (from "The Agent Interface Layer: Protocols, Tools and Trust Boundaries")
- [Redefining the software architect role for AI pipelines](https://www.wearedevelopers.com/videos/100190-architecture-3-0-from-90-to-99-999-reliability-in-building-ai-systems) (from "Architecture 3.0: From 90% to 99.999% Reliability in Building AI Systems")
- [Preserving engineering fundamentals in agentic development](https://www.wearedevelopers.com/videos/1897-agents-version-control-and-bunnies-daniel-siegl-david-payr) (from "Agents, Version Control and Bunnies - Daniel Siegl & David Payr")
- [Balancing developer autonomy with the adoption of coding agents](https://www.wearedevelopers.com/videos/100198-the-last-mile-of-ai-from-prototype-to-production) (from "The Last Mile of AI: From Prototype to Production")
- [Rethinking team structures around AI agent capabilities](https://www.wearedevelopers.com/videos/1539-agentic-devops-how-ai-powered-automation-transforms-software-delivery-on-github-and-azure) (from "Agentic DevOps: How AI-Powered Automation Transforms Software Delivery on GitHub and Azure")
- [Fusing developer experience and platform engineering for agentic SDLC](https://www.wearedevelopers.com/videos/100266-ai-won-t-fix-your-engineering-culture) (from "AI Won't Fix Your Engineering Culture")

## Related Articles

- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)
- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)
- [The Web We Broke (And Why AI Agents Are Paying the Price) - AgentCon Berlin](https://www.wearedevelopers.com/magazine/735-the-web-we-broke-and-why-ai-agents-are-paying-the-price-agentcon-berlin)

## Related Jobs

- [Principal Product Manager, Agent Platform](https://www.wearedevelopers.com/jobs/ext/277541-principal-product-manager-agent-platform) at **GitHub**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [Senior AI Agent Software Engineer (Go, Python) (m/f/x)](https://www.wearedevelopers.com/jobs/48277-senior-ai-agent-software-engineer-go-python-m-f-x) at **Dynatrace**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Principal Field Architect - AI Agents](https://www.wearedevelopers.com/jobs/ext/1442858-principal-field-architect-ai-agents) at **Twilio**
- [Tribe Lead - ( Software) Engineering Centre of Excllence](https://www.wearedevelopers.com/jobs/ext/1475530-tribe-lead-software-engineering-centre-of-excllence) at **SD Worx**