Blog
Brand marketing, leads and distribution at scale, from the field.
Practical guides for agencies and marketing teams: keeping one brand voice across dozens of accounts, measuring the leads from each one, and posting at scale without getting blocked.
7 min read
How Should an AI Agent Handle Holidays When It Posts for Many Different Audiences?
How an AI agent should schedule around holidays: map each account to its traditions, call get_holidays, read calendar_notes and block the evening before.
9 min read
The Agent Content Pipeline, End to End: Brief In, Per-Account Posts Out, Clicks Back, With Every Shager Call in Order
A full agent pipeline on Shager in TypeScript: brief, media, per-account captions, draft, client approval, staggered scheduling, delivery checks and clicks.
7 min read
First-Comment Lead Links With Agents: One Tracked Link per Account, Posted Right After the Post
How an agent uses Shager's first comment and per-account tracked links for leads: where links work on each network, which fields to set and how to measure it.
7 min read
Posting at Scale Without Getting Blocked: Pacing, Variety and Original Content
How agencies publish to dozens of accounts without restrictions: official APIs, staggered pacing, original content per account, and the networks' own rules.
8 min read
How to Choose a Distribution Platform for AI Agents: 12 Criteria
Twelve criteria for choosing a social distribution platform an AI agent can run: MCP and API access, scoped keys, audit, per-account variation and pricing.
8 min read
Multilingual Content Agents: Localising for Hebrew, Arabic and English Accounts Without Translating
Running content in several languages with AI agents: localisation versus translation, Hebrew and Arabic right-to-left pitfalls, and per-account captions.
8 min read
A Weekly Distribution Routine as a Claude Skill: Monday Drafts, Client Approvals, Friday Click Report
A Claude Code skill that runs an agency week in Shager: drafts from plan files, client approvals, scheduling only what's approved, and a Friday click report.
8 min read
Making a Website Agent-Ready: llms.txt, Markdown Pages, OpenAPI, api-catalog and MCP Server Cards
What an agent-ready website publishes: llms.txt, Markdown page versions, OpenAPI, the RFC 9727 api-catalog and an MCP server card, with shager.ai as example.
7 min read
API Keys for Agents: Read, Write, Publish, and an Audit Trail You Will Actually Check
Giving AI agents Shager API keys safely: what read, write and publish allow, the sandbox claim, key storage, rate limits, key rotation and the audit log.
8 min read
Build a Claude Skill for Shager: SKILL.md, Folder Layout and the Rules That Make Multi-Account Posting Repeatable
Package Shager distribution as a Claude Agent Skill: frontmatter that triggers well, reference files, a REST helper script, and where the skill should live.
6 min read
A Client Approval Workflow That Doesn't Stall Your Content Calendar
How agencies build client approvals that work: what needs sign-off, clear deadlines, approval links instead of email threads, and rules for silent clients.
7 min read
MCP Explained for Marketers: What It Is and Why Your Tools Need It
A plain-language guide to the Model Context Protocol for marketers: what MCP is, what servers and tools mean, how agents use them, and what to ask vendors.
7 min read
One Agent, Twelve Clients: Keeping Brands, Accounts and Links From Bleeding Into Each Other
How an agency runs one AI agent across many clients in Shager: a workspace per client, per-client context folders, naming rules and guards against cross-posts.
7 min read
Per-Account Lead Attribution: UTMs, Short Links and the First Comment
A practical guide to attributing leads to each page and profile: a consistent UTM scheme, one short link per account, first-comment links, and CRM handoff.
7 min read
The Weekly Client Report, Written by an Agent Every Monday Before You Wake Up
Build a weekly client report that an agent compiles from Shager: what was published, what failed, clicks per account and post, and how to join it to CRM leads.
7 min read
Client Connect Links: Access to Client Social Accounts Without Passwords
How agencies get publishing access to client Facebook, Instagram and YouTube accounts with a connect link: no shared passwords and no Shager account needed.
6 min read
Keeping One Brand Voice Across Dozens of Social Accounts
How agencies managing dozens of pages and profiles keep one consistent brand voice without duplicating posts: style guides, templates, groups and QA.
8 min read
Six Prompts That Make a Content Agent Safe to Run on Client Accounts
Copyable prompts for an AI content agent working through Shager: standing rules, weekly drafts, caption variation, scheduling, review and failure triage.
8 min read
Shager REST API Quickstart: From a Fresh Key to a Tracked Post on 40 Accounts in Seven Calls
A working tour of Shager's REST API in curl and TypeScript: auth, workspaces, channels, media, per-account drafts, scheduling, status checks and clicks.
7 min read
Scheduling Strategy for Agents: Time Zones, Staggering and Not Flooding Forty Pages at 9:00
How an AI agent should schedule posts across many accounts: ISO 8601 offsets, time zones and DST, stagger math, splitting groups across days, and safe cancels.
7 min read
Caption Variation per Account: Letting AI Rewrite Without Losing the Brand
How an AI agent can write a different caption for every account in a campaign while claims, offer and voice stay fixed, using per_channel in one create_post.
7 min read
One Vertical Video, Forty Accounts: How an Agent Ships Reels and Shorts Through Shager
A hands-on playbook for agents distributing short video: format checks, Reels and Shorts metadata, per-account captions, staggered dispatch and real MCP calls.
7 min read
Agent Self-Signup: How an AI Agent Opens a Shager Sandbox in One Call, and Why a Human Still Holds the Publish Button
An agent can open its own Shager sandbox with one POST. Here is the call, what the sandbox allows, the human claim step, and how publish rights get granted.
8 min read
Safety Rules for AI Agents Posting to Hundreds of Accounts
A rulebook for AI agents publishing to many social accounts: official APIs, scoped keys, varied captions, staggered dispatch, network limits and a stop plan.
7 min read
Can ChatGPT Post Through Shager? What Works Today, What Waits for OAuth, and the Three Routes That Ship Now
ChatGPT's MCP connectors need OAuth or no auth, so Shager's API-key server can't plug in yet. Here are the routes that work today and what OAuth will change.
8 min read
Measuring Leads From Agent-Published Content, Account by Account
How to tell whether agent-published posts produce leads: per-account short links and UTMs, campaign labels, get_analytics, CRM hidden fields and a weekly read.
7 min read
Add Shager to Cursor With .cursor/mcp.json: Turn Release Notes Into Drafts for Every Client Account
Configure Shager's remote MCP server in Cursor with a url and an env-backed Authorization header, then turn a changelog into per-account social drafts.
7 min read
Human Approval for Agent-Written Posts: Where to Put the Gate
Where human approval belongs when an AI agent writes and schedules social posts: scoped keys, draft-first runs, client approval links and what reviewers check.
7 min read
Shager in OpenAI Codex: config.toml, bearer_token_env_var and a Tool Allowlist That Keeps Drafts as Drafts
Set up Shager's remote MCP server in Codex CLI via config.toml or codex mcp add, read the key from an env var, restrict tools, and create a first draft.
8 min read
The Agency Operating Model When AI Agents Handle Distribution
How a social agency restructures roles, weekly rhythm, client workspaces and API keys when AI agents do distribution and people own strategy and approval.
7 min read
Connecting Shager to Claude Desktop: Custom Connector With Request Headers, or the mcp-remote Route
Two working ways to connect Claude Desktop to Shager's API-key MCP server: a custom connector with request headers, or mcp-remote in the desktop config file.
7 min read
No Content, No Existence: Why Silent Brands Vanish When Agents Choose
When agents and answer engines decide what people see, they draw on what is published and findable. A brand that doesn't publish consistently isn't found.
7 min read
Connect Shager to Claude Code: One Command, Then Draft Posts for 50 Accounts From Your Terminal
Add Shager's remote MCP server to Claude Code with claude mcp add and a bearer header, pick the right scope, verify it, and draft a first multi-account post.
7 min read
Why AI Agents Should Run Social Distribution, and What Humans Should Keep
Distribution is repetitive, rule-bound work across many accounts, which makes it a natural job for AI agents. Here is what to hand over and what humans keep.
Want to try it on your accounts?
Shager distributes, measures and gets client approval, all in one place.