Two agents, one experiment: feel the difference

The two agents

Agent GAJAH is the heavyweight. It runs a frontier-class model (OpenAI GPT-5.6 class), priced by OpenAI at $5.00 per million input tokens and $30.00 per million output tokens.

Agent KANCIL is the lightweight. It runs a budget model (DeepSeek v4 Flash), priced by DeepSeek at $0.14 per million input tokens and $0.28 per million output tokens.

Both agents carry identical tools and identical data. Only the brain differs. That is the whole point of the experiment: any difference you feel in the replies is the model, not the plumbing.

What to try

Ask anything about the Malaysian market. If you want a starting point, these questions exercise the datasets well:

• Compare median household income in Johor Bahru and Shah Alam.
• How many cafes are there in Penang?
• Which district in Selangor has the highest spending power?
• Profile the businesses within 2km of our venue.
• Where in Malaysia are pharmacies growing fastest?

The most useful move: send the same question to both agents, then compare. Look at three things. Depth: which answer goes further into the data? Caution: which agent flags what it does not know? Speed: which one comes back first? The differences are not subtle.

The rules of the sandbox

These rules are not decoration. They are a small, live example of the governance principles on the governance slide: constrain what an agent can reach, log what it does, and put a time limit on it.

• Replies take 30 to 60 seconds, and longer when the room is busy. The agents plan, query and check before answering; that takes time.
• Both agents are sandboxed on isolated infrastructure, with read-only access to public Malaysian datasets.
• They cannot act on the world. No email, no spending, no reach into any company system.
• Conversations are logged for the demonstration and deleted after. Do not send personal or confidential information.
• The agents stay live for one week after the workshop, so you can keep testing from your desk.

What you are feeling

Two gaps at once. The capability gap: the frontier model tends to reason further, hedge more honestly and handle messier questions. The cost gap: the budget model does respectable work at a fraction of the price. Neither agent is simply better. The lesson for an insights or marketing leader is that model choice is a management decision, not a technical one: match the model to the job, and pay for frontier reasoning only where the job demands it.

Sources