Reply.io
One sequence, multiple channels: email, LinkedIn steps, and calls together.
Reply.io builds a single sequence that mixes email with LinkedIn steps and call tasks rather than treating each channel as a separate campaign. Your agent resolves or creates the sequence, links a sending mailbox, enrolls the contacts, then stops and waits for your approval before it starts sending.
Reply.io is activation for a multichannel cadence. Sourcing and enrichment fill the contact list before it goes near a sequence.
things you can ask for
- “Create a sequence for this role and add an email plus a LinkedIn step to it”
- “Enroll these 200 contacts once Enrichley has validated them”
- “Have hyreflow Agent write the first email step before we enroll anyone”
- “Pause the sequence for anyone who's already replied”
works well with Reply.io
- Enrichley
validate the list before it goes into a live sequence
- hyreflow Agent
personalisation across the email and LinkedIn steps
- Wiza
LinkedIn URLs feed the LinkedIn steps in the same sequence
- Bullhorn
replies land on the record automatically
Skills that use Reply.io
A skill is a whole pipeline your agent already knows. These ones call Reply.io as part of the run.
Build an outreach sequence without losing control of the send
use whenyou have the list and now you need a cadence built, loaded and ready, with nothing going out until you say so
Build one cadence that moves between email, LinkedIn and the phone
use whenone channel is not getting answers and you want a single cadence where a contact who ignores the email meets a LinkedIn touch and then a call
Check your sending mailboxes and domain before a campaign goes out
use whena campaign is loaded and ready, and you want to know the mailboxes and the domain behind it are fit to send before you press start
Review what your campaigns are doing and what to change next
use whencampaigns are running or finished across one or more sequencers and nobody has looked at which ones earn replies and which only use up the list
What your agent reads before it touches Reply.io
Every tool ships with a written playbook, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Reply.io docs →Show the raw playbookwritten for the agent
HOW in lib/reply_io.py. Docs cached at reference/docs/reply_io/raw/endpoints.md.
Auth & config
- Base URL:
https://api.reply.io(every path sits under/v3) · Auth:Authorization: Bearer <key>(envREPLY_IO_API_KEY; never hardcode). Get the key from the Reply dashboard: Settings → API Key.
Approval gates (sending)
start_sequence(id)begins real outbound sending.add_contacts_to_sequenceinto a running sequence puts mail in flight. Approval-gate both: build the sequence and enroll into a paused state, pilot, confirm, then start.
Operations
Contacts: list_contacts, get_contact, create_contact, update_contact, search_contacts. Contact lists: list_contact_lists, add_contacts_to_list. Sequences: list_sequences, get_sequence, create_sequence, start_sequence, pause_sequence, get_sequence_stats, list_sequence_steps. Sequence contacts: list_sequence_contacts, add_contacts_to_sequence, remove_contacts_from_sequence, set_contacts_status_in_sequence, set_contacts_replied. Email accounts: list_email_accounts, list_sequence_email_accounts, link_email_account_to_sequence. Identity: whoami. Else → generic request().
Handoff
Activation layer: resolve/create a sequence → link mailboxes → create or import validated contacts → add_contacts_to_sequence → review → start_sequence. Replies feed back through get_sequence_stats and set_contacts_replied.
Field notes (production experience)
Field-shape note: these are vendor-native operational notes. The client returns the raw vendor JSON and uses the method names in this file — read field shapes accordingly (no normalized-wrapper /
result.data.prefix).
Activation order: resolve/create sequence -> link sending mailboxes -> create or import contacts -> enroll via add_contacts_to_sequence -> start_sequence -> monitor via get_sequence_stats. Always resolve the sequence ID before any write.
Gotchas (vendor-native):
- Scope model: API keys are scoped
domain:verb(e.g.contacts:read,sequences:operate). A key missingsequences:operatecan read sequences but cannot enroll or start anyone — the #1 confusing 403. - Bulk caps, not clamps:
add_contacts_to_sequence/remove_contacts_from_sequenceaccept up to 10,000 contact ids;set_contacts_status_in_sequence/set_contacts_repliedaccept up to 100. Over the cap the adapter raises rather than trimming. - Pagination:
top(page size, default 25, max 1000) +skip.top > 1000is rejected, not clamped — a clamp would make a paging loop silently skip records. update_contactis PATCH: omitted fields keep their current value, unlike a PUT.- Stats window is XOR:
get_sequence_statstakes either adateRangePreset(lastWeek/lastMonth/lastYear/allTime) or an explicitfrom/to, never both. - Sequence create needs both:
create_sequencerequires anameAND at least one step — a name-only create is rejected. - Replying finishes the contact:
set_contacts_repliedmarks a contact replied and that finishes them in the sequence. - Errors: RFC 9457
problem+json(title,status,detail,code,errors[]); a 401 has an empty body — checkWWW-Authenticateinstead. - Rate limit: 100 requests/minute and 3,000 requests/hour per user; stricter on reporting/stats endpoints. A 429 carries
Retry-After.