AI agents
SDR, voice and support agents; guardrails; evaluation.
17 Sept 2026 · 2 min read
AI SDR vs. human SDR: where each one wins
AI SDR agents are good at speed, coverage and consistency; human SDRs are good at judgement, relationships and unusual conversations. The right design uses both. Where to draw the line.
12 Feb 2026 · 2 min read
Choosing a model for a customer-facing agent: OpenAI, Anthropic, Gemini or open weights
The choice is less about benchmarks than about latency, instruction-following, safety behaviour, data handling and price at your volume. A practical way to decide, and why the answer is often two models.
29 Jan 2026 · 2 min read
What AI agents actually cost to run: tokens, voice minutes and the budget that makes sense
The per-conversation economics of chat and voice agents — model tokens, telephony, speech, orchestration — with the drivers that move the number and how to compare it honestly with a person.
15 Jan 2026 · 2 min read
AI agents and the CRM: what an agent should write back, and how
An agent that talks to customers and leaves nothing in the CRM has created a black hole. The fields, the summaries, the tasks and the flags every conversation should produce — and the format that makes them reportable.
25 Dec 2025 · 2 min read
Multilingual AI agents: serving customers in their language without a translation team
Language models handle dozens of languages well enough for support and sales conversations. How to design agents that detect language, respond natively, hand off to the right human, and stay culturally sensible.
11 Dec 2025 · 2 min read
The follow-up agent: chasing quotes and proposals politely, persistently and on time
Sent proposals go quiet because following up is awkward and forgettable. An agent that follows up on schedule, answers the simple questions, detects the real ones and hands them to the rep with context.
27 Nov 2025 · 2 min read
How to evaluate an AI agent before it talks to a customer
A test set of real conversations, scored on accuracy, tone, scope and hand-off — the evaluation loop that tells you whether an agent is ready, and catches regressions when you change the prompt.
13 Nov 2025 · 2 min read
AI support agents: resolving the repetitive half of tickets without frustrating the other half
Where an AI support agent genuinely helps (order status, how-to, policy questions), where it should step aside, and the metrics that separate real resolution from deflection.
30 Oct 2025 · 2 min read
Guardrails for customer-facing AI agents: scope, escalation, logging, review
An agent that talks to customers needs boundaries as much as capability. The four guardrails — a written scope, escalation triggers, full logging and a weekly review loop — that keep it useful and keep you out of trouble.
16 Oct 2025 · 2 min read
A voice agent for appointment booking: what good sounds like, and what it must never do
Voice agents now answer phones for clinics, salons, brokerages and service firms. The script design, the calendar integration, the escalation rules and the honesty requirements that make one feel like a receptionist rather than a phone tree.
