· ai · tools + guides
AI, in one place.
Every AI-adjacent thing on Briskly: the LLM token counter, the prompt caching calculator, the pricing comparisons, and the guides on system prompts, MCP servers, and picking between Claude, ChatGPT, and Gemini. All free, all built for practitioners who actually ship.
Tools.
· interactive · browser-only
· tool · 2026-05-22
AI tell killer
Stop ChatGPT, Claude, and Gemini from sounding like AI. Pick the patterns to kill (em dashes, the word 'comprehensive', sycophancy, hallucination, rule-of-three lists, and 16 more), get a paste-in prompt, a Claude Code rules block, and a Node.js lint script.
open →
· tool · 2026-05-22
AI output linter
Paste any AI-generated text. Real-time scan for em dashes, the word 'comprehensive', the AI vocabulary cluster, templated transitions, curly quotes, and the other regex-detectable tells. Findings show with line numbers and inline highlighting. Companion to the AI Tell Killer.
open →
· tool · 2026-05-22
AI slop detector
Paste any URL. Get a 0-100 AI-slop score from the visual template patterns AI site builders ship by default. Inter font, purple-to-blue gradients, shadcn rounded cards, 'Get Started' / 'Learn more' CTA pair, all-caps section labels, and 6 more rules. Findings include evidence snippets and specific fixes.
open →
· tool · 2026-05-22
Block AI crawlers
robots.txt generator that blocks the 22 most-active AI training and citation crawlers in 2026: GPTBot, ClaudeBot, Google-Extended, PerplexityBot, Bytespider, CCBot, Applebot-Extended, Meta-ExternalAgent, and more. Three presets, per-bot toggles, copy or download.
open →
· tool · 2026-04-21
LLM token counter
Count tokens across 23 LLMs including GPT-5.5, GPT-5.4, GPT-5, Claude 4.x, Gemini 3.x, and Llama 4. Exact tokenization for OpenAI; ~5-10% approximate for Claude/Gemini/Llama. Per-model input+output cost, context-window fill, in-browser.
open →
· tool · 2026-05-01
AI model picker
Five-question quiz that recommends one primary AI model plus two alternatives. Covers Claude, ChatGPT, Gemini, and Llama across 11 models. Picks based on use case, access method, context size, budget, and provider preference. Reasoning explained per recommendation.
open →
· tool · 2026-05-01
AI cost calculator
Project monthly API spend across 11 LLMs (Claude, GPT-5, Gemini, Llama). Inputs: request volume, prompt size, output length, prompt-cache hit rate. Six workload presets cover chatbot, RAG, agentic coding, content writing, summarizer, and high-volume API. Cheapest model and cheapest flagship highlighted.
open →
Guides.
· long-form · honest
· guide · 2026-04-21
Claude vs ChatGPT vs Gemini
An honest side-by-side of the three flagship LLMs. Capability table across 12 dimensions, pricing at every tier, and five scenario-specific picks for when each one is actually the right choice.
open →
· guide · 2026-04-27
Claude vs GPT-5.5 vs Gemini: API pricing compared
Current Claude API rates (Opus 4.7 at $5/$25, Sonnet 4.6 at $3/$15, Haiku 4.5 at $1/$5) benchmarked against GPT-5.5, GPT-5.4, Gemini 3.1 Pro, and Llama 4, with per-workload math for chatbots, RAG, and coding agents.
open →
· guide · 2026-04-21
Prompt caching explained
How Claude (90% off reads), OpenAI (up to 90% automatic), and Gemini (~75% with storage fees) implement prompt caching. Includes a live calculator that models your monthly savings under each provider.
open →
· guide · 2026-04-21
System prompts, explained
The instruction you give an LLM before the user's first message. Anatomy (role, context, behavior, examples), a copy-paste template, anti-patterns that break output, and how each provider interprets it.
open →
· guide · 2026-04-21
MCP server primer
What a Model Context Protocol server actually is, how to plug one into Claude Desktop in three steps, and how to ship your own to npm in an afternoon.
open →
· guide · 2026-04-22
How to make an invoice with AI
Three AI workflows for invoicing in 2026: Claude in Google Sheets, ChatGPT Canvas, Gemini in Workspace. Copy-paste prompt template, honest take on where AI helps and where it doesn't.
open →
· guide · 2026-04-22
How to set your freelance rate with AI
Market research with Claude, negotiation scripting with ChatGPT, cost-of-business math with Gemini. The prompts that work, the math AI still gets wrong, and a copy-paste template.
open →
· guide · 2026-04-23
How to draft a freelance contract with AI
Claude for clause drafting, ChatGPT Canvas for redline negotiation, Gemini for jurisdiction checks. The prompts that work, the clauses AI forgets, and when you still need an attorney.
open →
· guide · 2026-04-23
How to stop AI from using em dashes
Em dashes became the #1 AI-content detection tell in 2026. Copy-paste prompts for Claude, ChatGPT, and Gemini, plus a Claude Code skill file, a ChatGPT custom instruction, and a regex lint script you can drop into any project.
open →
· guide · 2026-04-23
AI agent platforms in 2026
Claude Agent SDK, OpenAI Agents, LangGraph, CrewAI, n8n, AutoGen. What each is good at, what each costs at realistic usage, and a four-question picking framework that matches the choice to the problem shape.
open →
· guide · 2026-04-23
AI workflow automation in 2026
Zapier, n8n, Make, Bardeen, Pipedream, Power Automate. AI-augmented workflow tools compared with real cost math at 5K-runs/month, plus when to use a workflow tool vs. an AI agent.
open →
· guide · 2026-04-20
Claude Design: first look
A working developer's review of Anthropic's Claude Design brand-system generator: what it does well, what it doesn't, and how Briskly used it to build the actual identity of this site.
open →
Integrations.
· npm · mcp · chrome
· integration · 2026-04-21 · ↗
briskly-mcp-llm-token-counter (npm)
MCP server that gives Claude Desktop, Cursor, and any MCP client the ability to count LLM tokens and estimate costs programmatically. Companion to the web token counter.
open ↗
· integration · 2026-05-01 · ↗
briskly-mcp-ai-model-picker (npm)
MCP server that lets Claude, Cursor, or any MCP client recommend an AI model for a given use case via pick_ai_model, list_ai_models, get_ai_model. Same decision engine as the web picker, deterministic outputs.
open ↗
· integration · 2026-05-01 · ↗
briskly-mcp-ai-cost-calculator (npm)
MCP server that lets agents estimate monthly AI API cost across 11 models. Tools: estimate_ai_cost, cheapest_ai_model (with optional tier constraint), list_cost_models. Cache-aware. Same math as the web cost calculator.
open ↗
Why a whole AI corner on a small-tools site
Briskly started as a small-tools studio: invoicing, rate calculators, email signatures. The AI corner grew as a response to one observation: every resource about working with LLMs either reads like a product pitch (provider blogs, launch posts) or reads like a LinkedIn hype tour ("I tried GPT-5.4 and you won't believe…"). The practical, vendor-neutral, actually-useful version was missing.
What you find here: current API pricing that isn't marketing-washed, calculators that run actual math on your workload, and comparison pieces that name the model that wins for each specific task rather than hand-waving about "it depends." Everything is written after using the tools on real projects, not after reading the press release.
The LLM token counter is the central hub. It runs exact tokenization for OpenAI models via the bundled gpt-tokenizer library, and ~5-10% approximate counts for Claude, Gemini, and Llama (whose tokenizers aren't browser-compatible). Most of the guides cross-link to it because counting tokens is the first step of almost every AI-cost decision.
Updates
Pricing, model versions, and provider features change constantly. We try to update within a week when a major change lands (e.g., Claude Opus dropping from $15/$75 to $5/$25 in early 2026, or the GPT-5.4 family release). Everything on this page shows its last-updated date.
Missing something? Email us. The next guide is usually whatever a reader asked for twice in the same week.