Gong
Use Gong for sales-call evidence. Call metadata alone is not enough for a deep
dive that asks what happened in customer conversations.
Answer Questions With Gong's Own Search First
Gong's MCP (ask_account, ask_deal, generate_brief) searches and analyzes
the calls server-side and answers in seconds. That is how Claude answers Gong
questions, and it is the default here too.
- A question about an account, deal, customer, competitor, or topic ("what did
X say about Y", risks, objections, themes, next steps, call prep) →
run-gong-native-insight first, one consolidated call. Do not page /calls
or /calls/extensive, and do not pull transcripts, to answer a question.
- Reach for the raw paths below only when the user needs verbatim quotes, an
exact count, or proof that something was absent across all calls, or when the
native operations are not connected (
gong-native-insights lists them).
- If a blocking Gong request returns a size-limit error, stop paging and switch
to the native operation or a narrower
gong-calls search. Never retry the
same wide window.
Actions
gong-native-insights — lists the connected provider-native qualitative
synthesis operations (ask_account, ask_deal, generate_brief) and their
schemas. It never calls Gong AI or spends a credit request.
run-gong-native-insight — sends one of those operations through Gong's
connected MCP. This is the first choice for questions, themes, risks,
summaries, and deck narrative when the native tools are connected. One
invocation makes one Gong AI request (one credit request), so put related
sub-questions in one call. It is on by default; a workspace owner can turn it
off with configure-gong-native-insights, which never blocks the raw
evidence path.
account-deep-dive — first choice for a named account/deal when the answer
needs HubSpot CRM context alongside Gong. For a question about what was said
in the calls, use run-gong-native-insight first. It searches by
account/deal/company/contact domain, loads Gong call details, and returns
compact transcript excerpts for synthesis.
gong-calls — bounded convenience reads: list recent calls, search by
company/domain/person/email, fetch a single transcript by call ID, or return
transcript excerpts for a small matching cohort. Its transcriptQuery is a
local scan after batched transcript retrieval, not Gong's server-side
keyword search.
For exhaustive, count, or absence-sensitive Gong work, use the raw provider API surface:
use provider-api-catalog / provider-api-docs, then stage /calls/extensive
or another raw endpoint with provider-api-request. Reduce staged tracker or
call data with query-staged-dataset or a Data Program. Use
provider-corpus-job only when raw transcript bodies are required and no
native/indexed search can answer the question.
Route Synthesis and Evidence Separately
- Use
run-gong-native-insight to answer the question where Gong retrieves
and analyzes evidence internally. Its result is provider synthesis: coverage
is unknown and raw transcript evidence is unavailable, so say that when the
user asked for completeness.
- Use
gong-calls or provider-corpus-job for quotes, exact counts, transcript
records, coverage-sensitive claims, and proof that something was absent.
- Consolidate related native questions into one narrowly scoped request. Each
native operation independently consumes a Gong credit request, so do not make
one call per slide, bullet, or sub-question.
- From a sibling app, ask Analytics a natural-language question by default.
Analytics owns Gong/HubSpot routing, source coverage, credentials, transcript
strategy, joins, and synthesis. Use
call-agent's direct action + input
mode only when a trusted integration explicitly names one stable semantic
read contract and supplies its complete bounded input. Never use direct
actions as a workaround for a slow or failed delegated run.
Account Search Algorithm
Gong search pages POST /v2/calls/extensive directly with the requested date
window and party data (not GET /v2/calls, which returns no parties). Each call
is matched against both:
- Title variants: the call title contains a generated search variant.
- External parties: an external participant's name, email, or domain
matches a generated search variant.
This catches calls titled "Builder <> Acme" when you search
"Acme Corp" by matching the "acme" name variant or "@acme.com" domain variant.
The lib generates variants by stripping deal suffixes (- New Deal, - Fusion),
corporate suffixes (Group, Inc, Corp, LLC), and deriving first word and
email domain — always including the raw original. Variants shorter than 3 chars
are filtered. This is why a broad company search can find more calls than an
exact-title search.
Customer-Voice Extraction (externalMonologues)
When analyzing customer sentiment, objections, or voice of the customer:
- Use
getEnrichedTranscript / request enriched transcripts — it maps each
monologue to speaker identity and affiliation.
- Only use
externalMonologues for customer/prospect statements. Monologues
with affiliation === "Internal" are your own team's speech — never surface
these as "what the customer said."
- The
externalMonologues field on an enriched transcript is the pre-filtered
customer-voice signal; use it directly.
Patterns
For account or deal deep dives:
- Ask
run-gong-native-insight first for what customers said, risks,
objections, and next steps. Call account-deep-dive first when the request
also needs CRM context, contacts, stages, amount, close date, or an overall
opportunity narrative, or when native operations are not connected.
- Use
gong-calls for targeted follow-up searches by account name, domain,
person, or email.
- Set
includeTranscripts=true when the user asks for context, risks,
objections, next steps, decision process, sentiment, or a "deep dive".
- Use
transcriptLimit around 3-5 for a first pass. For broad coverage of a
named account, increase to 10-20 — the action supports up to 50. Increase
when the returned calls don't cover the time window or key people you need.
For a bounded "review all calls" request with at most 50 matches, make one
call with exhaustive=true, after, before, and
includeTranscripts=true; do not split discovery and transcripts into
separate agent tool calls.
- Use the compact transcript excerpts returned by
includeTranscripts=true.
Do not fetch raw individual transcripts unless the user asks for exhaustive
quoting, debugging, or export.
- Ground qualitative findings in the transcript excerpts and state how many
calls were inspected.
- For bounded account coverage, use
cursor/offset only when the cohort is
intentionally bounded. If the action reports truncation, treat coverage as
incomplete and switch to tracker staging with provider-api-request plus
query-staged-dataset or a Data Program, or to provider-corpus-job when
raw transcript bodies are required. Do not increase the limit or keep
paging gong-calls for broad scans. Do not use
gong-calls(exhaustive=true) or one blocking provider-api-request call as
the analysis. Stage the raw response and reduce it with a Data Program or
query-staged-dataset; use provider-corpus-job for checkpointed transcript
batches when raw bodies are necessary.
Quota and Coverage Rules
- Every Gong list or transcript page consumes provider quota. Budget pages and
transcript batches before starting a broad scan; do not spend quota retrying
the same bounded action after it reports incomplete coverage.
- A terminal HTTP 429 is terminal for that attempt. The shared provider
transport may perform bounded cooldown/retry handling from
Retry-After, but
the agent must not add another retry loop. Report the rate-limit failure and
switch to the staged tracker or checkpointed provider-corpus-job path only
if that route is still appropriate.
- Exhaustive, count, and absence claims require complete coverage of the stated
cohort. If any page, transcript batch, or provider request fails or is
truncated, report the gap and do not make the claim.
Example:
gong-calls(company: "The Knot", days: 180, limit: 20, includeTranscripts: true, transcriptLimit: 10)
Gong search is best-effort: it matches title plus external participant names,
emails, and domains through /calls/extensive. Treat call details and transcript
excerpts as evidence; treat missing coverage as a gap, not proof that the topic
never came up.
Title/party matching is discovery only. Never use a title pre-filter as proof
that a phrase is absent from transcripts.
If transcript loading fails for a call, report that gap instead of inferring the
conversation content from title, date, or participants.
When a single transcript is needed, gong-calls(transcript: "...") returns
compact extracted text by default. Set rawTranscript=true only for
debugging/export, and never pass raw transcript payloads into save-analysis.
Complete-Coverage Transcript Scan
When the question is "do ANY of these calls mention X?" or "how many calls across
this cohort mention X?" — where missing a single call makes the answer wrong — do
NOT conclude absence from a sampled includeTranscripts result. Exhaustive
claims require complete coverage of every call in the stated cohort. Choose the
smallest complete path for the bounded cohort:
Configured keyword tracker. If the requested term is already a Gong
keyword tracker exposed in API results, use provider-api-request against
/calls/extensive with contentSelector.exposedFields.content.trackers.
Stage the paginated calls, then flatten and filter tracker ids, names, or
phrases with query-staged-dataset or a Data Program. This is the preferred
broad keyword path because Gong has already indexed the tracker. It does not
answer arbitrary terms that are not configured as trackers.
Named account, up to 50 calls, qualitative review. Make one gong-calls
call with exhaustive=true, a bounded after/before window, and
includeTranscripts=true. The action discovers every matching call and
fetches transcript excerpts in batches, returning transcriptCoverage. Do
not fetch the same call IDs one at a time afterward.
Bounded arbitrary mention/absence search, up to 200 calls. Make one
gong-calls
call with exhaustive=true, the date window, transcriptQuery, and an
adequate transcriptScanLimit. This is a bounded local scan after batched
transcript retrieval. Report its coverage fields and only make an absence
claim when coverage is complete.
Larger or multi-account arbitrary corpus. Use
provider-api-catalog(provider: "gong") and its corpusRecipes if you need
the exact shape. Stage call ids with the raw API, then use
provider-corpus-job with mode: "batch-search" and 20-call transcript
batches. The canonical request is POST /calls/transcript with
batch.itemBodyPath: "filter.callIds", batch.responseItemsPath: "callTranscripts", batch.batchSize: 20, search.textPaths: ["transcript"], and search.idPaths: ["callId"]. Feed the staged/discovered
call ids through batch.inputDatasetId + batch.inputValuePath or through
batch.items. This is a durable full scan, not a server-side keyword query;
do not implement it as a per-call loop in run-code or a delegated agent.
When delegating a corpus chunk to an Agent Teams sub-agent, include the exact
staged dataset id or scratch/... path and the output/checkpoint path in the
task brief. The child starts with a clean context and must read the staged
input before making any provider request. If that input is unavailable, it
must report the missing input rather than re-fetching the entire Gong corpus.
- Use
run-code only for joins/reductions around the corpus path. After
the transcript job exists, use run-code, query-staged-dataset, or job
results to join hits back to deals/accounts, compute variants, dedupe, and
format evidence. A run-code loop over gong-calls(transcript: id) is a
fallback for small or awkward sets, not the default for broad scans.
Report coverage explicitly: deals in cohort, calls discovered, calls scanned, and
matches found. Never turn "I inspected a sample" into "no call mentions X".
Limits (Current)
| Parameter |
Default |
Max |
limit (calls returned) |
8 |
200 |
transcriptLimit |
3 |
50 |
transcriptMaxChars |
8 000 |
100 000 |
For large account deep-dives or competitive analyses spanning many calls, use
limit: 50-200 and transcriptLimit: 20-50. For very large datasets, use the
checkpointed provider-corpus-job path rather than paging the full Gong call
list inside one agent action.
1---2name: gong3description: >-4 Search Gong call metadata and transcript excerpts for sales-call analysis,5 customer conversations, objections, risks, and next steps.6metadata:7 source: https://skillmd.com/skills/builderio/gong8---910# Gong1112Use Gong for sales-call evidence. Call metadata alone is not enough for a deep13dive that asks what happened in customer conversations.1415## Answer Questions With Gong's Own Search First1617Gong's MCP (`ask_account`, `ask_deal`, `generate_brief`) searches and analyzes18the calls server-side and answers in seconds. That is how Claude answers Gong19questions, and it is the default here too.2021- A question about an account, deal, customer, competitor, or topic ("what did22 X say about Y", risks, objections, themes, next steps, call prep) →23 `run-gong-native-insight` first, one consolidated call. Do not page `/calls`24 or `/calls/extensive`, and do not pull transcripts, to answer a question.25- Reach for the raw paths below only when the user needs verbatim quotes, an26 exact count, or proof that something was absent across all calls, or when the27 native operations are not connected (`gong-native-insights` lists them).28- If a blocking Gong request returns a size-limit error, stop paging and switch29 to the native operation or a narrower `gong-calls` search. Never retry the30 same wide window.3132## Actions3334- `gong-native-insights` — lists the connected provider-native qualitative35 synthesis operations (`ask_account`, `ask_deal`, `generate_brief`) and their36 schemas. It never calls Gong AI or spends a credit request.37- `run-gong-native-insight` — sends one of those operations through Gong's38 connected MCP. This is the first choice for questions, themes, risks,39 summaries, and deck narrative when the native tools are connected. One40 invocation makes one Gong AI request (one credit request), so put related41 sub-questions in one call. It is on by default; a workspace owner can turn it42 off with `configure-gong-native-insights`, which never blocks the raw43 evidence path.44- `account-deep-dive` — first choice for a named account/deal when the answer45 needs HubSpot CRM context alongside Gong. For a question about what was said46 in the calls, use `run-gong-native-insight` first. It searches by47 account/deal/company/contact domain, loads Gong call details, and returns48 compact transcript excerpts for synthesis.49- `gong-calls` — bounded convenience reads: list recent calls, search by50 company/domain/person/email, fetch a single transcript by call ID, or return51 transcript excerpts for a small matching cohort. Its `transcriptQuery` is a52 local scan after batched transcript retrieval, not Gong's server-side53 keyword search.5455For exhaustive, count, or absence-sensitive Gong work, use the raw provider API surface:56use `provider-api-catalog` / `provider-api-docs`, then stage `/calls/extensive`57or another raw endpoint with `provider-api-request`. Reduce staged tracker or58call data with `query-staged-dataset` or a Data Program. Use59`provider-corpus-job` only when raw transcript bodies are required and no60native/indexed search can answer the question.6162## Route Synthesis and Evidence Separately6364- Use `run-gong-native-insight` to answer the question where Gong retrieves65 and analyzes evidence internally. Its result is provider synthesis: coverage66 is unknown and raw transcript evidence is unavailable, so say that when the67 user asked for completeness.68- Use `gong-calls` or `provider-corpus-job` for quotes, exact counts, transcript69 records, coverage-sensitive claims, and proof that something was absent.70- Consolidate related native questions into one narrowly scoped request. Each71 native operation independently consumes a Gong credit request, so do not make72 one call per slide, bullet, or sub-question.73- From a sibling app, ask Analytics a natural-language question by default.74 Analytics owns Gong/HubSpot routing, source coverage, credentials, transcript75 strategy, joins, and synthesis. Use `call-agent`'s direct `action` + `input`76 mode only when a trusted integration explicitly names one stable semantic77 read contract and supplies its complete bounded input. Never use direct78 actions as a workaround for a slow or failed delegated run.7980## Account Search Algorithm8182Gong search pages `POST /v2/calls/extensive` directly with the requested date83window and party data (not `GET /v2/calls`, which returns no parties). Each call84is matched against both:85861. **Title variants**: the call title contains a generated search variant.872. **External parties**: an external participant's name, email, or domain88 matches a generated search variant.8990This catches calls titled "Builder <> Acme" when you search91"Acme Corp" by matching the "acme" name variant or "@acme.com" domain variant.92The lib generates variants by stripping deal suffixes (`- New Deal`, `- Fusion`),93corporate suffixes (`Group`, `Inc`, `Corp`, `LLC`), and deriving first word and94email domain — always including the raw original. Variants shorter than 3 chars95are filtered. This is why a broad company search can find more calls than an96exact-title search.9798## Customer-Voice Extraction (externalMonologues)99100When analyzing customer sentiment, objections, or voice of the customer:101102- Use `getEnrichedTranscript` / request enriched transcripts — it maps each103 monologue to speaker identity and affiliation.104- **Only use `externalMonologues`** for customer/prospect statements. Monologues105 with `affiliation === "Internal"` are your own team's speech — never surface106 these as "what the customer said."107- The `externalMonologues` field on an enriched transcript is the pre-filtered108 customer-voice signal; use it directly.109110## Patterns111112For account or deal deep dives:1131141. Ask `run-gong-native-insight` first for what customers said, risks,115 objections, and next steps. Call `account-deep-dive` first when the request116 also needs CRM context, contacts, stages, amount, close date, or an overall117 opportunity narrative, or when native operations are not connected.1182. Use `gong-calls` for targeted follow-up searches by account name, domain,119 person, or email.1203. Set `includeTranscripts=true` when the user asks for context, risks,121 objections, next steps, decision process, sentiment, or a "deep dive".1224. Use `transcriptLimit` around 3-5 for a first pass. For broad coverage of a123 named account, increase to 10-20 — the action supports up to 50. Increase124 when the returned calls don't cover the time window or key people you need.125 For a bounded "review all calls" request with at most 50 matches, make one126 call with `exhaustive=true`, `after`, `before`, and127 `includeTranscripts=true`; do not split discovery and transcripts into128 separate agent tool calls.1295. Use the compact transcript excerpts returned by `includeTranscripts=true`.130 Do not fetch raw individual transcripts unless the user asks for exhaustive131 quoting, debugging, or export.1326. Ground qualitative findings in the transcript excerpts and state how many133 calls were inspected.1347. For bounded account coverage, use `cursor`/offset only when the cohort is135 intentionally bounded. If the action reports truncation, treat coverage as136 incomplete and switch to tracker staging with `provider-api-request` plus137 `query-staged-dataset` or a Data Program, or to `provider-corpus-job` when138 raw transcript bodies are required. Do not increase the limit or keep139 paging `gong-calls` for broad scans. Do not use140 `gong-calls(exhaustive=true)` or one blocking `provider-api-request` call as141 the analysis. Stage the raw response and reduce it with a Data Program or142 `query-staged-dataset`; use `provider-corpus-job` for checkpointed transcript143 batches when raw bodies are necessary.144145## Quota and Coverage Rules146147- Every Gong list or transcript page consumes provider quota. Budget pages and148 transcript batches before starting a broad scan; do not spend quota retrying149 the same bounded action after it reports incomplete coverage.150- A terminal HTTP 429 is terminal for that attempt. The shared provider151 transport may perform bounded cooldown/retry handling from `Retry-After`, but152 the agent must not add another retry loop. Report the rate-limit failure and153 switch to the staged tracker or checkpointed `provider-corpus-job` path only154 if that route is still appropriate.155- Exhaustive, count, and absence claims require complete coverage of the stated156 cohort. If any page, transcript batch, or provider request fails or is157 truncated, report the gap and do not make the claim.158159Example:160161```txt162gong-calls(company: "The Knot", days: 180, limit: 20, includeTranscripts: true, transcriptLimit: 10)163```164165Gong search is best-effort: it matches title plus external participant names,166emails, and domains through `/calls/extensive`. Treat call details and transcript167excerpts as evidence; treat missing coverage as a gap, not proof that the topic168never came up.169170Title/party matching is discovery only. Never use a title pre-filter as proof171that a phrase is absent from transcripts.172173If transcript loading fails for a call, report that gap instead of inferring the174conversation content from title, date, or participants.175176When a single transcript is needed, `gong-calls(transcript: "...")` returns177compact extracted text by default. Set `rawTranscript=true` only for178debugging/export, and never pass raw transcript payloads into `save-analysis`.179180## Complete-Coverage Transcript Scan181182When the question is "do ANY of these calls mention X?" or "how many calls across183this cohort mention X?" — where missing a single call makes the answer wrong — do184NOT conclude absence from a sampled `includeTranscripts` result. Exhaustive185claims require complete coverage of every call in the stated cohort. Choose the186smallest complete path for the bounded cohort:1871881. **Configured keyword tracker.** If the requested term is already a Gong189 keyword tracker exposed in API results, use `provider-api-request` against190 `/calls/extensive` with `contentSelector.exposedFields.content.trackers`.191 Stage the paginated calls, then flatten and filter tracker ids, names, or192 phrases with `query-staged-dataset` or a Data Program. This is the preferred193 broad keyword path because Gong has already indexed the tracker. It does not194 answer arbitrary terms that are not configured as trackers.1951962. **Named account, up to 50 calls, qualitative review.** Make one `gong-calls`197 call with `exhaustive=true`, a bounded `after`/`before` window, and198 `includeTranscripts=true`. The action discovers every matching call and199 fetches transcript excerpts in batches, returning `transcriptCoverage`. Do200 not fetch the same call IDs one at a time afterward.2012023. **Bounded arbitrary mention/absence search, up to 200 calls.** Make one203 `gong-calls`204 call with `exhaustive=true`, the date window, `transcriptQuery`, and an205 adequate `transcriptScanLimit`. This is a bounded local scan after batched206 transcript retrieval. Report its coverage fields and only make an absence207 claim when coverage is complete.2082094. **Larger or multi-account arbitrary corpus.** Use210 `provider-api-catalog(provider: "gong")` and its `corpusRecipes` if you need211 the exact shape. Stage call ids with the raw API, then use212 `provider-corpus-job` with `mode: "batch-search"` and 20-call transcript213 batches. The canonical request is `POST /calls/transcript` with214 `batch.itemBodyPath: "filter.callIds"`, `batch.responseItemsPath:215"callTranscripts"`, `batch.batchSize: 20`, `search.textPaths:216["transcript"]`, and `search.idPaths: ["callId"]`. Feed the staged/discovered217 call ids through `batch.inputDatasetId` + `batch.inputValuePath` or through218 `batch.items`. This is a durable full scan, not a server-side keyword query;219 do not implement it as a per-call loop in `run-code` or a delegated agent.220221When delegating a corpus chunk to an Agent Teams sub-agent, include the exact222staged dataset id or `scratch/...` path and the output/checkpoint path in the223task brief. The child starts with a clean context and must read the staged224input before making any provider request. If that input is unavailable, it225must report the missing input rather than re-fetching the entire Gong corpus.2262275. **Use `run-code` only for joins/reductions around the corpus path.** After228 the transcript job exists, use `run-code`, `query-staged-dataset`, or job229 results to join hits back to deals/accounts, compute variants, dedupe, and230 format evidence. A `run-code` loop over `gong-calls(transcript: id)` is a231 fallback for small or awkward sets, not the default for broad scans.232233Report coverage explicitly: deals in cohort, calls discovered, calls scanned, and234matches found. Never turn "I inspected a sample" into "no call mentions X".235236## Limits (Current)237238| Parameter | Default | Max |239| ------------------------ | ------- | ------- |240| `limit` (calls returned) | 8 | 200 |241| `transcriptLimit` | 3 | 50 |242| `transcriptMaxChars` | 8 000 | 100 000 |243244For large account deep-dives or competitive analyses spanning many calls, use245`limit: 50-200` and `transcriptLimit: 20-50`. For very large datasets, use the246checkpointed `provider-corpus-job` path rather than paging the full Gong call247list inside one agent action.