AWS shares winning design of Cisco agent competition
Understand this story
Cisco hosted an AWS AI League tournament at Cisco Transformation Fest 4.0, with 1,200 engineers taking part in two challenges: agentic AI and model fine-tuning. Champion Nishanth Aluhonnu won an all-access pass to AWS re:Invent 2026. AWS subsequently shared design lessons from the winning agent. According to AWS, during the finals participants could not modify code, tools, or prompts, and could only give a short guiding instruction before each round began; tool return results and system prompts did not count toward the score, but everything the agent wrote (including tool call parameters) did count. The AWS account team provided training before the event so that engineers with no prior agentic AI experience could compete from day one. AWS said the lessons from the 2026 winning agent can be applied beyond the competition, and explained how organizations can run their own AWS AI League.
AI overview based on source reports · Updated 14 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogFrom learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI League
Cisco used AWS AI League, a gamified competition with a learn workshop, live-leaderboard build phase, and game-show finale, as part of its Transformation Fest program, which has reached around 2,000 engineers over four editions. In 2025 Cisco engineer Hemanth V won the first AWS AI League global title at AWS re:Invent 2025, and in 2026 1,200 Cisco engineers competed in an agentic AI tournament at Cisco Transformation Fest 4.0, where Nishanth Aluhonnu won a full pass to AWS re:Invent 2026. The post also details the winning agent's design choices, including minimizing output tokens, using a single agent instead of sub-agents, moving route planning into an AWS Lambda tool, and prioritizing high-value challenges.
Activity for this story
- Current comparable activity
- 6
- Peak comparable activity
- 10Nov 20 03:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.