Skip to main content
Theme — Build something that makes a customer forget they’re talking to an AI.A common piece of client feedback is that our agents still feel robotic: they complete the task, but customers can tell they’re talking to a bot. The challenge isn’t making the agent smarter — it’s making the interaction feel human. By the end, we want a clearer answer to one question: what makes a customer forget they’re talking to an AI?

The Challenge

Improve the perceived humanness of the Tala Hindi collections agent. The goal is not a better script — it’s a more human conversational experience.

You may modify

  • System prompts & prompt structure
  • Behavioral instructions
  • Memory & state management
  • Conversation planning & context management
  • Dialogue policies & response strategies
  • Few-shot examples & evaluation frameworks
  • Model layer: RAG, fine-tuning

You may not modify

  • The underlying foundation models
  • STT or TTS providers
  • Core collections business logic
  • Compliance requirements

Start with a Hypothesis

Every participant begins by choosing one specific hypothesis about what makes conversation feel human. A narrow, well-tested idea is worth more than a broad pile of random tweaks — the goal is to learn something about human conversation, not just to improve the agent.
Example hypotheses:
  • Agents sound more human when they use fragments rather than complete sentences.
  • …when they explicitly track emotional state.
  • …when they reference earlier parts of the conversation.
  • …when they ask one thing at a time.
  • …when they adapt formality and code-mixing to the customer.
  • …when they avoid generic empathy phrases.
  • …when they respond to multiple intents in a single user turn.

Human Conversation Dimensions

Your solution should improve one or more of these:

Listening

Demonstrates understanding without parroting the customer’s words.

Adaptiveness

Changes behavior based on the customer’s situation, tone, and responses.

Conversational Flow

Natural rather than scripted — smooth transitions, pacing, and turn-taking.

Social Intelligence

Adjusts tone, formality, warmth, and language appropriately.

Memory & Continuity

Remembers and uses relevant context from earlier in the conversation.

Repair & Recovery

Handles interruptions, misunderstandings, and ASR errors gracefully.

Strategic Effectiveness

Moves toward a productive outcome without sounding robotic or aggressive.

Things we want less of

Repeating customer responses · generic empathy statements · long monologues · repetitive phrasing · overly formal language · scripted transitions · one-size-fits-all behavior · massive phrase banks and hardcoded branching.
We’re looking for principles that generalize, not larger scripts.

Constraints

Compliance failures are automatic disqualifiers. All mandatory disclosures must remain intact, and the agent must be truthful, avoid threats or intimidation, preserve customer dignity, and never hallucinate policies, figures, or commitments.
Performance & practicality. Naturalness must not come at the cost of severe latency, excessive verbosity, or impractical operational complexity. Solutions should remain realistic for production deployment at scale.

Evaluation

The primary objective is agent naturalness. Submissions are evaluated on how natural the agent feels during interactions — the specific techniques, tools, or approaches used to get there earn no extra points. Only the end result and overall conversational naturalness count.
All submissions are evaluated against the same customer personas:

Hardship

Recently lost their job and cannot pay the full amount.

Hostile

Frustrated and confrontational.

Evasive

Avoids committing to any payment date.

Cooperative

Willing to engage but needs flexibility.

Judging Criteria

How We Evaluate with Okareo

We measure naturalness with Okareo, which runs automated, recorded phone calls against your agent using a fixed set of customer personas — so every submission faces identical conversations.

How a simulation runs

1

Automated call

Okareo places a live phone call to your agent’s number.
2

Synthetic caller

A simulated caller plays a fixed persona — a defined personality, situation, and goal — and holds a real multi-turn conversation in Hindi/Hinglish.
3

Capture

Audio, transcript, and trace are recorded together on a single timeline.
4

Scoring

Each call is graded by the automated checks below; naturalness is additionally scored by a blind human listening test.
Personas, checks, and the judge model are frozen across all submissions, so the scorecard compares agents — not test conditions.

Personas

Alongside the four scored customer personas (Hardship, Hostile, Evasive, Cooperative), five operational probes run as a correctness gate: Busy-in-intro, Wrong person, Already paid, STT name variant, and Silence / gibberish.

Checks

Naturalness (scored) — applied to the four customer personas: Integrity — applied to every call (the first three are disqualifying): Operational routing — one per operational persona:

Disqualification & scoring

A submission is disqualified if the Compliance Gate, Internal-Reasoning Leakage, or Function / Tool Calls check fails on any persona — regardless of how natural it sounds.
For non-disqualified submissions, each check feeds the judging criterion shown in its Feeds column. Pass/Fail components score as the percentage of passing calls; a check that a given call doesn’t exercise returns N/A and is excluded from the math (it neither helps nor hurts).

Running Your Own Simulations

The Okareo workspace is a shared account used by all participants (engineers contribute individually).
1

Share your number

Provide a phone number wired to your agent.
2

We verify

We run an initial simulation to confirm the setup connects and runs cleanly, with no issues.
3

Run it yourself

Once verified, trigger simulations on your own from the shared Okareo account and review the recording, transcript, and scorecard for each run.
Because the account is shared, label your runs with your name so results stay easy to find, and avoid editing the shared personas or checks.

Timeline

Demo Format

Each participant has 5 minutes.
1

Hypothesis (1 min)

What theory about human conversation are you testing?
2

Approach (1 min)

What changes did you make, and why?
3

Before vs. After (2 min)

Show the baseline and the improved behavior on the same scenario.
4

Results & Learning (1 min)

Share evidence or observations, and complete the sentence: “We learned that conversations feel more human when ______.”

Winning

The winning project won’t necessarily be the most sophisticated one. It will be the one that teaches us something important about human conversation — a principle that can improve every Awaaz AI agent we build.